{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.10","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Sign Language Recognition Challenge\n\nThe goal of this competition is to classify American Sign Language (ASL) signs.\n\nThe landmarks were extracted from raw videos with the MediaPipe holistic model and are asked to predict the sign from this data.","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom tqdm.notebook import tqdm\nplt.style.use(\"seaborn-colorblind\")","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:44:39.48124Z","iopub.execute_input":"2023-07-31T11:44:39.481732Z","iopub.status.idle":"2023-07-31T11:44:41.001099Z","shell.execute_reply.started":"2023-07-31T11:44:39.481703Z","shell.execute_reply":"2023-07-31T11:44:40.999994Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stderr","text":"/tmp/ipykernel_28/3004115372.py:6: MatplotlibDeprecationWarning: The seaborn styles shipped by Matplotlib are deprecated since 3.6, as they no longer correspond to the styles shipped by seaborn. However, they will remain available as 'seaborn-v0_8-<style>'. Alternatively, directly use the seaborn API instead.\n  plt.style.use(\"seaborn-colorblind\")\n","output_type":"stream"}]},{"cell_type":"code","source":"!ls ../input/asl-fingerspelling/ -GFlash --color","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:44:41.006507Z","iopub.execute_input":"2023-07-31T11:44:41.00899Z","iopub.status.idle":"2023-07-31T11:44:42.218794Z","shell.execute_reply.started":"2023-07-31T11:44:41.008953Z","shell.execute_reply":"2023-07-31T11:44:42.217277Z"},"trusted":true},"execution_count":2,"outputs":[{"name":"stdout","text":"total 9.9M\n   0 drwxr-xr-x 4 nobody    0 Jun 11 02:15 \u001b[0m\u001b[01;34m.\u001b[0m/\n4.0K drwxr-xr-x 3 root   4.0K Jul 31 11:43 \u001b[01;34m..\u001b[0m/\n4.0K -rw-r--r-- 1 nobody  405 Jun 11 02:15 character_to_prediction_index.json\n   0 drwxr-xr-x 2 nobody    0 Jun 11 02:15 \u001b[01;34msupplemental_landmarks\u001b[0m/\n4.9M -rw-r--r-- 1 nobody 4.9M Jun 11 02:15 supplemental_metadata.csv\n5.0M -rw-r--r-- 1 nobody 5.0M Jun 11 02:15 train.csv\n   0 drwxr-xr-x 2 nobody    0 Jun 11 02:15 \u001b[01;34mtrain_landmarks\u001b[0m/\n","output_type":"stream"}]},{"cell_type":"markdown","source":"# Data EDA","metadata":{}},{"cell_type":"code","source":"BASE_DIR = '../input/asl-fingerspelling/'\ntrain = pd.read_csv('/kaggle/input/asl-fingerspelling/train.csv')\ntrain.shape","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:44:42.223184Z","iopub.execute_input":"2023-07-31T11:44:42.223963Z","iopub.status.idle":"2023-07-31T11:44:42.491218Z","shell.execute_reply.started":"2023-07-31T11:44:42.223921Z","shell.execute_reply":"2023-07-31T11:44:42.49007Z"},"trusted":true},"execution_count":3,"outputs":[{"execution_count":3,"output_type":"execute_result","data":{"text/plain":"(67208, 5)"},"metadata":{}}]},{"cell_type":"code","source":"import pandas as pd \ntrain = pd.read_csv('/kaggle/input/asl-fingerspelling/train.csv')\ntrain","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:44:42.49533Z","iopub.execute_input":"2023-07-31T11:44:42.49574Z","iopub.status.idle":"2023-07-31T11:44:42.66455Z","shell.execute_reply.started":"2023-07-31T11:44:42.495704Z","shell.execute_reply":"2023-07-31T11:44:42.66336Z"},"trusted":true},"execution_count":4,"outputs":[{"execution_count":4,"output_type":"execute_result","data":{"text/plain":"                                     path     file_id  sequence_id  \\\n0         train_landmarks/5414471.parquet     5414471   1816796431   \n1         train_landmarks/5414471.parquet     5414471   1816825349   \n2         train_landmarks/5414471.parquet     5414471   1816909464   \n3         train_landmarks/5414471.parquet     5414471   1816967051   \n4         train_landmarks/5414471.parquet     5414471   1817123330   \n...                                   ...         ...          ...   \n67203  train_landmarks/2118949241.parquet  2118949241    388192924   \n67204  train_landmarks/2118949241.parquet  2118949241    388225542   \n67205  train_landmarks/2118949241.parquet  2118949241    388232076   \n67206  train_landmarks/2118949241.parquet  2118949241    388235284   \n67207  train_landmarks/2118949241.parquet  2118949241    388332538   \n\n       participant_id                          phrase  \n0                 217                    3 creekhouse  \n1                 107                 scales/kuhaylah  \n2                   1             1383 william lanier  \n3                  63               988 franklin lane  \n4                  89       6920 northeast 661st road  \n...               ...                             ...  \n67203              88                    431-366-2913  \n67204             154                    994-392-3850  \n67205              95  https://www.tianjiagenomes.com  \n67206              36               90 kerwood circle  \n67207             176                      802 co 66b  \n\n[67208 rows x 5 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>path</th>\n      <th>file_id</th>\n      <th>sequence_id</th>\n      <th>participant_id</th>\n      <th>phrase</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>train_landmarks/5414471.parquet</td>\n      <td>5414471</td>\n      <td>1816796431</td>\n      <td>217</td>\n      <td>3 creekhouse</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>train_landmarks/5414471.parquet</td>\n      <td>5414471</td>\n      <td>1816825349</td>\n      <td>107</td>\n      <td>scales/kuhaylah</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>train_landmarks/5414471.parquet</td>\n      <td>5414471</td>\n      <td>1816909464</td>\n      <td>1</td>\n      <td>1383 william lanier</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>train_landmarks/5414471.parquet</td>\n      <td>5414471</td>\n      <td>1816967051</td>\n      <td>63</td>\n      <td>988 franklin lane</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>train_landmarks/5414471.parquet</td>\n      <td>5414471</td>\n      <td>1817123330</td>\n      <td>89</td>\n      <td>6920 northeast 661st road</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>67203</th>\n      <td>train_landmarks/2118949241.parquet</td>\n      <td>2118949241</td>\n      <td>388192924</td>\n      <td>88</td>\n      <td>431-366-2913</td>\n    </tr>\n    <tr>\n      <th>67204</th>\n      <td>train_landmarks/2118949241.parquet</td>\n      <td>2118949241</td>\n      <td>388225542</td>\n      <td>154</td>\n      <td>994-392-3850</td>\n    </tr>\n    <tr>\n      <th>67205</th>\n      <td>train_landmarks/2118949241.parquet</td>\n      <td>2118949241</td>\n      <td>388232076</td>\n      <td>95</td>\n      <td>https://www.tianjiagenomes.com</td>\n    </tr>\n    <tr>\n      <th>67206</th>\n      <td>train_landmarks/2118949241.parquet</td>\n      <td>2118949241</td>\n      <td>388235284</td>\n      <td>36</td>\n      <td>90 kerwood circle</td>\n    </tr>\n    <tr>\n      <th>67207</th>\n      <td>train_landmarks/2118949241.parquet</td>\n      <td>2118949241</td>\n      <td>388332538</td>\n      <td>176</td>\n      <td>802 co 66b</td>\n    </tr>\n  </tbody>\n</table>\n<p>67208 rows × 5 columns</p>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"# Train.csv has the path to each parquet file, the particpant id, sequence_id and sign.\ntrain.head()","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:44:42.668063Z","iopub.execute_input":"2023-07-31T11:44:42.672297Z","iopub.status.idle":"2023-07-31T11:44:42.691498Z","shell.execute_reply.started":"2023-07-31T11:44:42.672261Z","shell.execute_reply":"2023-07-31T11:44:42.689771Z"},"trusted":true},"execution_count":5,"outputs":[{"execution_count":5,"output_type":"execute_result","data":{"text/plain":"                              path  file_id  sequence_id  participant_id  \\\n0  train_landmarks/5414471.parquet  5414471   1816796431             217   \n1  train_landmarks/5414471.parquet  5414471   1816825349             107   \n2  train_landmarks/5414471.parquet  5414471   1816909464               1   \n3  train_landmarks/5414471.parquet  5414471   1816967051              63   \n4  train_landmarks/5414471.parquet  5414471   1817123330              89   \n\n                      phrase  \n0               3 creekhouse  \n1            scales/kuhaylah  \n2        1383 william lanier  \n3          988 franklin lane  \n4  6920 northeast 661st road  ","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>path</th>\n      <th>file_id</th>\n      <th>sequence_id</th>\n      <th>participant_id</th>\n      <th>phrase</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>train_landmarks/5414471.parquet</td>\n      <td>5414471</td>\n      <td>1816796431</td>\n      <td>217</td>\n      <td>3 creekhouse</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>train_landmarks/5414471.parquet</td>\n      <td>5414471</td>\n      <td>1816825349</td>\n      <td>107</td>\n      <td>scales/kuhaylah</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>train_landmarks/5414471.parquet</td>\n      <td>5414471</td>\n      <td>1816909464</td>\n      <td>1</td>\n      <td>1383 william lanier</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>train_landmarks/5414471.parquet</td>\n      <td>5414471</td>\n      <td>1816967051</td>\n      <td>63</td>\n      <td>988 franklin lane</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>train_landmarks/5414471.parquet</td>\n      <td>5414471</td>\n      <td>1817123330</td>\n      <td>89</td>\n      <td>6920 northeast 661st road</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"markdown","source":"# **WHAT PHRASES ARE WE TRYING TO PREDICT**\n- There are 46518 unique phrases\n- Ranging from 1 to 17 examples of each  ","metadata":{}},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nfig, ax = plt.subplots(figsize=(8, 8))\ntrain[\"phrase\"].value_counts().head(50).sort_values(ascending=True).plot(\n    kind=\"barh\", ax=ax, title=\"Top 50 Signs in Training Dataset\"\n)\nax.set_xlabel(\"Number of Training Examples\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:44:42.695252Z","iopub.execute_input":"2023-07-31T11:44:42.695692Z","iopub.status.idle":"2023-07-31T11:44:43.882319Z","shell.execute_reply.started":"2023-07-31T11:44:42.695647Z","shell.execute_reply":"2023-07-31T11:44:43.88132Z"},"trusted":true},"execution_count":6,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 800x800 with 1 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nfig, ax = plt.subplots(figsize=(8, 8))\ntrain[\"phrase\"].value_counts().tail(50).sort_values(ascending=True).plot(\n    kind=\"barh\", ax=ax, title=\"Bottom 50 Signs in Training Dataset\"\n)\nax.set_xlabel(\"Number of Training Examples\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:44:43.883441Z","iopub.execute_input":"2023-07-31T11:44:43.883806Z","iopub.status.idle":"2023-07-31T11:44:45.067702Z","shell.execute_reply.started":"2023-07-31T11:44:43.883773Z","shell.execute_reply":"2023-07-31T11:44:45.066496Z"},"trusted":true},"execution_count":7,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 800x800 with 1 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"markdown","source":"# Parquet Landmark Data\n- Each Parquet file is in the path:\n - train_landmark_files/[train/supplemental].parquet\n - The parquet's associated phrase can be found in train.csv","metadata":{}},{"cell_type":"markdown","source":"# Pull an example parquet file data...\n\nWe pull an example landmark file for the phrase \"surprise az\"","metadata":{}},{"cell_type":"code","source":"example_fn = train.query('phrase == \"surprise az\"')[\"path\"].values[0]\nexample_landmark = pd.read_parquet(f\"{BASE_DIR}/{example_fn}\")\nexample_landmark.head()","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:44:45.069716Z","iopub.execute_input":"2023-07-31T11:44:45.070439Z","iopub.status.idle":"2023-07-31T11:45:03.220452Z","shell.execute_reply.started":"2023-07-31T11:44:45.0704Z","shell.execute_reply":"2023-07-31T11:45:03.219382Z"},"trusted":true},"execution_count":8,"outputs":[{"execution_count":8,"output_type":"execute_result","data":{"text/plain":"             frame  x_face_0  x_face_1  x_face_2  x_face_3  x_face_4  \\\nsequence_id                                                            \n892546335        0  0.558532  0.544893  0.550765  0.531709  0.542882   \n892546335        1  0.558485  0.538496  0.546902  0.526788  0.536074   \n892546335        2  0.559387  0.538431  0.547265  0.526393  0.535808   \n892546335        3  0.557837  0.541629  0.549719  0.527716  0.538818   \n892546335        4  0.553872  0.537255  0.545412  0.522412  0.534153   \n\n             x_face_5  x_face_6  x_face_7  x_face_8  ...  z_right_hand_11  \\\nsequence_id                                          ...                    \n892546335    0.542395  0.543382  0.461938  0.542168  ...        -0.025242   \n892546335    0.535973  0.538563  0.463473  0.537398  ...              NaN   \n892546335    0.535540  0.537791  0.468848  0.536576  ...        -0.118818   \n892546335    0.537770  0.537678  0.463155  0.535218  ...        -0.129440   \n892546335    0.532779  0.531839  0.458245  0.528752  ...              NaN   \n\n             z_right_hand_12  z_right_hand_13  z_right_hand_14  \\\nsequence_id                                                      \n892546335          -0.037157        -0.016177        -0.034248   \n892546335                NaN              NaN              NaN   \n892546335          -0.137097        -0.086207        -0.124947   \n892546335          -0.154642        -0.102356        -0.143587   \n892546335                NaN              NaN              NaN   \n\n             z_right_hand_15  z_right_hand_16  z_right_hand_17  \\\nsequence_id                                                      \n892546335          -0.046090        -0.051801        -0.047187   \n892546335                NaN              NaN              NaN   \n892546335          -0.141636        -0.152644        -0.121944   \n892546335          -0.172341        -0.192996        -0.147066   \n892546335                NaN              NaN              NaN   \n\n             z_right_hand_18  z_right_hand_19  z_right_hand_20  \nsequence_id                                                     \n892546335          -0.061533        -0.066047        -0.067060  \n892546335                NaN              NaN              NaN  \n892546335          -0.153051        -0.164828        -0.173849  \n892546335          -0.180508        -0.197671        -0.212346  \n892546335                NaN              NaN              NaN  \n\n[5 rows x 1630 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>frame</th>\n      <th>x_face_0</th>\n      <th>x_face_1</th>\n      <th>x_face_2</th>\n      <th>x_face_3</th>\n      <th>x_face_4</th>\n      <th>x_face_5</th>\n      <th>x_face_6</th>\n      <th>x_face_7</th>\n      <th>x_face_8</th>\n      <th>...</th>\n      <th>z_right_hand_11</th>\n      <th>z_right_hand_12</th>\n      <th>z_right_hand_13</th>\n      <th>z_right_hand_14</th>\n      <th>z_right_hand_15</th>\n      <th>z_right_hand_16</th>\n      <th>z_right_hand_17</th>\n      <th>z_right_hand_18</th>\n      <th>z_right_hand_19</th>\n      <th>z_right_hand_20</th>\n    </tr>\n    <tr>\n      <th>sequence_id</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>892546335</th>\n      <td>0</td>\n      <td>0.558532</td>\n      <td>0.544893</td>\n      <td>0.550765</td>\n      <td>0.531709</td>\n      <td>0.542882</td>\n      <td>0.542395</td>\n      <td>0.543382</td>\n      <td>0.461938</td>\n      <td>0.542168</td>\n      <td>...</td>\n      <td>-0.025242</td>\n      <td>-0.037157</td>\n      <td>-0.016177</td>\n      <td>-0.034248</td>\n      <td>-0.046090</td>\n      <td>-0.051801</td>\n      <td>-0.047187</td>\n      <td>-0.061533</td>\n      <td>-0.066047</td>\n      <td>-0.067060</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>1</td>\n      <td>0.558485</td>\n      <td>0.538496</td>\n      <td>0.546902</td>\n      <td>0.526788</td>\n      <td>0.536074</td>\n      <td>0.535973</td>\n      <td>0.538563</td>\n      <td>0.463473</td>\n      <td>0.537398</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>2</td>\n      <td>0.559387</td>\n      <td>0.538431</td>\n      <td>0.547265</td>\n      <td>0.526393</td>\n      <td>0.535808</td>\n      <td>0.535540</td>\n      <td>0.537791</td>\n      <td>0.468848</td>\n      <td>0.536576</td>\n      <td>...</td>\n      <td>-0.118818</td>\n      <td>-0.137097</td>\n      <td>-0.086207</td>\n      <td>-0.124947</td>\n      <td>-0.141636</td>\n      <td>-0.152644</td>\n      <td>-0.121944</td>\n      <td>-0.153051</td>\n      <td>-0.164828</td>\n      <td>-0.173849</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>3</td>\n      <td>0.557837</td>\n      <td>0.541629</td>\n      <td>0.549719</td>\n      <td>0.527716</td>\n      <td>0.538818</td>\n      <td>0.537770</td>\n      <td>0.537678</td>\n      <td>0.463155</td>\n      <td>0.535218</td>\n      <td>...</td>\n      <td>-0.129440</td>\n      <td>-0.154642</td>\n      <td>-0.102356</td>\n      <td>-0.143587</td>\n      <td>-0.172341</td>\n      <td>-0.192996</td>\n      <td>-0.147066</td>\n      <td>-0.180508</td>\n      <td>-0.197671</td>\n      <td>-0.212346</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>4</td>\n      <td>0.553872</td>\n      <td>0.537255</td>\n      <td>0.545412</td>\n      <td>0.522412</td>\n      <td>0.534153</td>\n      <td>0.532779</td>\n      <td>0.531839</td>\n      <td>0.458245</td>\n      <td>0.528752</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 1630 columns</p>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"example_landmark","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:45:03.222153Z","iopub.execute_input":"2023-07-31T11:45:03.222936Z","iopub.status.idle":"2023-07-31T11:45:03.279547Z","shell.execute_reply.started":"2023-07-31T11:45:03.222895Z","shell.execute_reply":"2023-07-31T11:45:03.27842Z"},"trusted":true},"execution_count":9,"outputs":[{"execution_count":9,"output_type":"execute_result","data":{"text/plain":"             frame  x_face_0  x_face_1  x_face_2  x_face_3  x_face_4  \\\nsequence_id                                                            \n892546335        0  0.558532  0.544893  0.550765  0.531709  0.542882   \n892546335        1  0.558485  0.538496  0.546902  0.526788  0.536074   \n892546335        2  0.559387  0.538431  0.547265  0.526393  0.535808   \n892546335        3  0.557837  0.541629  0.549719  0.527716  0.538818   \n892546335        4  0.553872  0.537255  0.545412  0.522412  0.534153   \n...            ...       ...       ...       ...       ...       ...   \n926078741      167  0.666573  0.680770  0.679185  0.663492  0.680639   \n926078741      168  0.662258  0.676808  0.675712  0.659671  0.676574   \n926078741      169  0.661971  0.670780  0.670854  0.655241  0.670645   \n926078741      170  0.660110  0.664442  0.664654  0.648924  0.664258   \n926078741      171  0.655350  0.660850  0.660410  0.644145  0.660438   \n\n             x_face_5  x_face_6  x_face_7  x_face_8  ...  z_right_hand_11  \\\nsequence_id                                          ...                    \n892546335    0.542395  0.543382  0.461938  0.542168  ...        -0.025242   \n892546335    0.535973  0.538563  0.463473  0.537398  ...              NaN   \n892546335    0.535540  0.537791  0.468848  0.536576  ...        -0.118818   \n892546335    0.537770  0.537678  0.463155  0.535218  ...        -0.129440   \n892546335    0.532779  0.531839  0.458245  0.528752  ...              NaN   \n...               ...       ...       ...       ...  ...              ...   \n926078741    0.679611  0.676069  0.551874  0.673817  ...        -0.334243   \n926078741    0.675623  0.672584  0.550114  0.670699  ...              NaN   \n926078741    0.670540  0.669942  0.547087  0.669080  ...        -0.413789   \n926078741    0.664099  0.663613  0.542146  0.662831  ...        -0.316694   \n926078741    0.659709  0.657623  0.536247  0.655869  ...        -0.267454   \n\n             z_right_hand_12  z_right_hand_13  z_right_hand_14  \\\nsequence_id                                                      \n892546335          -0.037157        -0.016177        -0.034248   \n892546335                NaN              NaN              NaN   \n892546335          -0.137097        -0.086207        -0.124947   \n892546335          -0.154642        -0.102356        -0.143587   \n892546335                NaN              NaN              NaN   \n...                      ...              ...              ...   \n926078741          -0.392523        -0.163864        -0.238234   \n926078741                NaN              NaN              NaN   \n926078741          -0.489348        -0.185839        -0.294575   \n926078741          -0.364578        -0.173660        -0.243761   \n926078741          -0.321842        -0.112076        -0.172052   \n\n             z_right_hand_15  z_right_hand_16  z_right_hand_17  \\\nsequence_id                                                      \n892546335          -0.046090        -0.051801        -0.047187   \n892546335                NaN              NaN              NaN   \n892546335          -0.141636        -0.152644        -0.121944   \n892546335          -0.172341        -0.192996        -0.147066   \n892546335                NaN              NaN              NaN   \n...                      ...              ...              ...   \n926078741          -0.311453        -0.362199        -0.159862   \n926078741                NaN              NaN              NaN   \n926078741          -0.395767        -0.459715        -0.202480   \n926078741          -0.303576        -0.345224        -0.176801   \n926078741          -0.238773        -0.284961        -0.103608   \n\n             z_right_hand_18  z_right_hand_19  z_right_hand_20  \nsequence_id                                                     \n892546335          -0.061533        -0.066047        -0.067060  \n892546335                NaN              NaN              NaN  \n892546335          -0.153051        -0.164828        -0.173849  \n892546335          -0.180508        -0.197671        -0.212346  \n892546335                NaN              NaN              NaN  \n...                      ...              ...              ...  \n926078741          -0.223101        -0.269810        -0.305507  \n926078741                NaN              NaN              NaN  \n926078741          -0.280212        -0.346813        -0.399406  \n926078741          -0.239134        -0.279785        -0.310076  \n926078741          -0.149414        -0.188530        -0.219580  \n\n[159858 rows x 1630 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>frame</th>\n      <th>x_face_0</th>\n      <th>x_face_1</th>\n      <th>x_face_2</th>\n      <th>x_face_3</th>\n      <th>x_face_4</th>\n      <th>x_face_5</th>\n      <th>x_face_6</th>\n      <th>x_face_7</th>\n      <th>x_face_8</th>\n      <th>...</th>\n      <th>z_right_hand_11</th>\n      <th>z_right_hand_12</th>\n      <th>z_right_hand_13</th>\n      <th>z_right_hand_14</th>\n      <th>z_right_hand_15</th>\n      <th>z_right_hand_16</th>\n      <th>z_right_hand_17</th>\n      <th>z_right_hand_18</th>\n      <th>z_right_hand_19</th>\n      <th>z_right_hand_20</th>\n    </tr>\n    <tr>\n      <th>sequence_id</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>892546335</th>\n      <td>0</td>\n      <td>0.558532</td>\n      <td>0.544893</td>\n      <td>0.550765</td>\n      <td>0.531709</td>\n      <td>0.542882</td>\n      <td>0.542395</td>\n      <td>0.543382</td>\n      <td>0.461938</td>\n      <td>0.542168</td>\n      <td>...</td>\n      <td>-0.025242</td>\n      <td>-0.037157</td>\n      <td>-0.016177</td>\n      <td>-0.034248</td>\n      <td>-0.046090</td>\n      <td>-0.051801</td>\n      <td>-0.047187</td>\n      <td>-0.061533</td>\n      <td>-0.066047</td>\n      <td>-0.067060</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>1</td>\n      <td>0.558485</td>\n      <td>0.538496</td>\n      <td>0.546902</td>\n      <td>0.526788</td>\n      <td>0.536074</td>\n      <td>0.535973</td>\n      <td>0.538563</td>\n      <td>0.463473</td>\n      <td>0.537398</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>2</td>\n      <td>0.559387</td>\n      <td>0.538431</td>\n      <td>0.547265</td>\n      <td>0.526393</td>\n      <td>0.535808</td>\n      <td>0.535540</td>\n      <td>0.537791</td>\n      <td>0.468848</td>\n      <td>0.536576</td>\n      <td>...</td>\n      <td>-0.118818</td>\n      <td>-0.137097</td>\n      <td>-0.086207</td>\n      <td>-0.124947</td>\n      <td>-0.141636</td>\n      <td>-0.152644</td>\n      <td>-0.121944</td>\n      <td>-0.153051</td>\n      <td>-0.164828</td>\n      <td>-0.173849</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>3</td>\n      <td>0.557837</td>\n      <td>0.541629</td>\n      <td>0.549719</td>\n      <td>0.527716</td>\n      <td>0.538818</td>\n      <td>0.537770</td>\n      <td>0.537678</td>\n      <td>0.463155</td>\n      <td>0.535218</td>\n      <td>...</td>\n      <td>-0.129440</td>\n      <td>-0.154642</td>\n      <td>-0.102356</td>\n      <td>-0.143587</td>\n      <td>-0.172341</td>\n      <td>-0.192996</td>\n      <td>-0.147066</td>\n      <td>-0.180508</td>\n      <td>-0.197671</td>\n      <td>-0.212346</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>4</td>\n      <td>0.553872</td>\n      <td>0.537255</td>\n      <td>0.545412</td>\n      <td>0.522412</td>\n      <td>0.534153</td>\n      <td>0.532779</td>\n      <td>0.531839</td>\n      <td>0.458245</td>\n      <td>0.528752</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>926078741</th>\n      <td>167</td>\n      <td>0.666573</td>\n      <td>0.680770</td>\n      <td>0.679185</td>\n      <td>0.663492</td>\n      <td>0.680639</td>\n      <td>0.679611</td>\n      <td>0.676069</td>\n      <td>0.551874</td>\n      <td>0.673817</td>\n      <td>...</td>\n      <td>-0.334243</td>\n      <td>-0.392523</td>\n      <td>-0.163864</td>\n      <td>-0.238234</td>\n      <td>-0.311453</td>\n      <td>-0.362199</td>\n      <td>-0.159862</td>\n      <td>-0.223101</td>\n      <td>-0.269810</td>\n      <td>-0.305507</td>\n    </tr>\n    <tr>\n      <th>926078741</th>\n      <td>168</td>\n      <td>0.662258</td>\n      <td>0.676808</td>\n      <td>0.675712</td>\n      <td>0.659671</td>\n      <td>0.676574</td>\n      <td>0.675623</td>\n      <td>0.672584</td>\n      <td>0.550114</td>\n      <td>0.670699</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>926078741</th>\n      <td>169</td>\n      <td>0.661971</td>\n      <td>0.670780</td>\n      <td>0.670854</td>\n      <td>0.655241</td>\n      <td>0.670645</td>\n      <td>0.670540</td>\n      <td>0.669942</td>\n      <td>0.547087</td>\n      <td>0.669080</td>\n      <td>...</td>\n      <td>-0.413789</td>\n      <td>-0.489348</td>\n      <td>-0.185839</td>\n      <td>-0.294575</td>\n      <td>-0.395767</td>\n      <td>-0.459715</td>\n      <td>-0.202480</td>\n      <td>-0.280212</td>\n      <td>-0.346813</td>\n      <td>-0.399406</td>\n    </tr>\n    <tr>\n      <th>926078741</th>\n      <td>170</td>\n      <td>0.660110</td>\n      <td>0.664442</td>\n      <td>0.664654</td>\n      <td>0.648924</td>\n      <td>0.664258</td>\n      <td>0.664099</td>\n      <td>0.663613</td>\n      <td>0.542146</td>\n      <td>0.662831</td>\n      <td>...</td>\n      <td>-0.316694</td>\n      <td>-0.364578</td>\n      <td>-0.173660</td>\n      <td>-0.243761</td>\n      <td>-0.303576</td>\n      <td>-0.345224</td>\n      <td>-0.176801</td>\n      <td>-0.239134</td>\n      <td>-0.279785</td>\n      <td>-0.310076</td>\n    </tr>\n    <tr>\n      <th>926078741</th>\n      <td>171</td>\n      <td>0.655350</td>\n      <td>0.660850</td>\n      <td>0.660410</td>\n      <td>0.644145</td>\n      <td>0.660438</td>\n      <td>0.659709</td>\n      <td>0.657623</td>\n      <td>0.536247</td>\n      <td>0.655869</td>\n      <td>...</td>\n      <td>-0.267454</td>\n      <td>-0.321842</td>\n      <td>-0.112076</td>\n      <td>-0.172052</td>\n      <td>-0.238773</td>\n      <td>-0.284961</td>\n      <td>-0.103608</td>\n      <td>-0.149414</td>\n      <td>-0.188530</td>\n      <td>-0.219580</td>\n    </tr>\n  </tbody>\n</table>\n<p>159858 rows × 1630 columns</p>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"unique_frames = example_landmark[\"frame\"].nunique()\n\nprint(\n    f\"The file has {unique_frames} unique frames\"\n)\n","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:45:03.285156Z","iopub.execute_input":"2023-07-31T11:45:03.287142Z","iopub.status.idle":"2023-07-31T11:45:03.295816Z","shell.execute_reply.started":"2023-07-31T11:45:03.287112Z","shell.execute_reply":"2023-07-31T11:45:03.294545Z"},"trusted":true},"execution_count":10,"outputs":[{"name":"stdout","text":"The file has 555 unique frames\n","output_type":"stream"}]},{"cell_type":"markdown","source":"Lets Compare for a bunch of parquet files what type of data we have.\n- We notice the number of frames is not consistent\n- Almost every file has 4 types of landmarks: face, left_hand, pose and right_hand.","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nBASE_DIR = '../input/asl-fingerspelling/'\ntrain = pd.read_csv('/kaggle/input/asl-fingerspelling/train.csv')\nsurprise_az_files = train.query('phrase == \"surprise az\"')[\"path\"].values\nfor i, f in enumerate(surprise_az_files):\n    example_landmark = pd.read_parquet(f\"{BASE_DIR}/{f}\")\n    unique_frames = example_landmark[\"frame\"].nunique()\n    print(f\"The file has {unique_frames} unique frames \")\n    if i == 20:\n        break","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:45:03.29799Z","iopub.execute_input":"2023-07-31T11:45:03.298484Z","iopub.status.idle":"2023-07-31T11:49:03.77058Z","shell.execute_reply.started":"2023-07-31T11:45:03.298449Z","shell.execute_reply":"2023-07-31T11:49:03.768949Z"},"trusted":true},"execution_count":11,"outputs":[{"name":"stdout","text":"The file has 555 unique frames \nThe file has 555 unique frames \nThe file has 485 unique frames \nThe file has 485 unique frames \nThe file has 776 unique frames \nThe file has 807 unique frames \nThe file has 669 unique frames \nThe file has 540 unique frames \nThe file has 565 unique frames \nThe file has 519 unique frames \nThe file has 519 unique frames \nThe file has 541 unique frames \nThe file has 598 unique frames \nThe file has 576 unique frames \nThe file has 482 unique frames \nThe file has 594 unique frames \nThe file has 602 unique frames \n","output_type":"stream"}]},{"cell_type":"markdown","source":"In the training data provided to us, let us see how many instances are there for surprise az phrase","metadata":{}},{"cell_type":"code","source":"train.query('phrase == \"surprise az\"')","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:03.772111Z","iopub.execute_input":"2023-07-31T11:49:03.773254Z","iopub.status.idle":"2023-07-31T11:49:03.796781Z","shell.execute_reply.started":"2023-07-31T11:49:03.773215Z","shell.execute_reply":"2023-07-31T11:49:03.795285Z"},"trusted":true},"execution_count":12,"outputs":[{"execution_count":12,"output_type":"execute_result","data":{"text/plain":"                                     path     file_id  sequence_id  \\\n9064    train_landmarks/349393104.parquet   349393104    894682073   \n9746    train_landmarks/349393104.parquet   349393104    918130651   \n11169   train_landmarks/425182931.parquet   425182931   1121952165   \n11784   train_landmarks/425182931.parquet   425182931   1140531985   \n13881   train_landmarks/474255203.parquet   474255203     53122870   \n18454   train_landmarks/546816846.parquet   546816846   1436504564   \n28650   train_landmarks/933868835.parquet   933868835    838563709   \n32275  train_landmarks/1098899348.parquet  1098899348   1848989014   \n34841  train_landmarks/1133664520.parquet  1133664520    560352351   \n36523  train_landmarks/1255240050.parquet  1255240050    581413666   \n37000  train_landmarks/1255240050.parquet  1255240050    595834010   \n42615  train_landmarks/1405046009.parquet  1405046009    240058490   \n45040  train_landmarks/1497621680.parquet  1497621680   1047290809   \n46508  train_landmarks/1557244878.parquet  1557244878    331596218   \n54788  train_landmarks/1865557033.parquet  1865557033   2123641268   \n60357  train_landmarks/1969985709.parquet  1969985709   1595884623   \n61578  train_landmarks/1997878546.parquet  1997878546    711000266   \n\n       participant_id       phrase  \n9064               20  surprise az  \n9746              242  surprise az  \n11169             102  surprise az  \n11784             113  surprise az  \n13881             254  surprise az  \n18454              36  surprise az  \n28650              72  surprise az  \n32275              68  surprise az  \n34841             254  surprise az  \n36523             128  surprise az  \n37000              59  surprise az  \n42615              10  surprise az  \n45040             230  surprise az  \n46508             168  surprise az  \n54788             203  surprise az  \n60357             136  surprise az  \n61578             161  surprise az  ","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>path</th>\n      <th>file_id</th>\n      <th>sequence_id</th>\n      <th>participant_id</th>\n      <th>phrase</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>9064</th>\n      <td>train_landmarks/349393104.parquet</td>\n      <td>349393104</td>\n      <td>894682073</td>\n      <td>20</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>9746</th>\n      <td>train_landmarks/349393104.parquet</td>\n      <td>349393104</td>\n      <td>918130651</td>\n      <td>242</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>11169</th>\n      <td>train_landmarks/425182931.parquet</td>\n      <td>425182931</td>\n      <td>1121952165</td>\n      <td>102</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>11784</th>\n      <td>train_landmarks/425182931.parquet</td>\n      <td>425182931</td>\n      <td>1140531985</td>\n      <td>113</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>13881</th>\n      <td>train_landmarks/474255203.parquet</td>\n      <td>474255203</td>\n      <td>53122870</td>\n      <td>254</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>18454</th>\n      <td>train_landmarks/546816846.parquet</td>\n      <td>546816846</td>\n      <td>1436504564</td>\n      <td>36</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>28650</th>\n      <td>train_landmarks/933868835.parquet</td>\n      <td>933868835</td>\n      <td>838563709</td>\n      <td>72</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>32275</th>\n      <td>train_landmarks/1098899348.parquet</td>\n      <td>1098899348</td>\n      <td>1848989014</td>\n      <td>68</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>34841</th>\n      <td>train_landmarks/1133664520.parquet</td>\n      <td>1133664520</td>\n      <td>560352351</td>\n      <td>254</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>36523</th>\n      <td>train_landmarks/1255240050.parquet</td>\n      <td>1255240050</td>\n      <td>581413666</td>\n      <td>128</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>37000</th>\n      <td>train_landmarks/1255240050.parquet</td>\n      <td>1255240050</td>\n      <td>595834010</td>\n      <td>59</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>42615</th>\n      <td>train_landmarks/1405046009.parquet</td>\n      <td>1405046009</td>\n      <td>240058490</td>\n      <td>10</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>45040</th>\n      <td>train_landmarks/1497621680.parquet</td>\n      <td>1497621680</td>\n      <td>1047290809</td>\n      <td>230</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>46508</th>\n      <td>train_landmarks/1557244878.parquet</td>\n      <td>1557244878</td>\n      <td>331596218</td>\n      <td>168</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>54788</th>\n      <td>train_landmarks/1865557033.parquet</td>\n      <td>1865557033</td>\n      <td>2123641268</td>\n      <td>203</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>60357</th>\n      <td>train_landmarks/1969985709.parquet</td>\n      <td>1969985709</td>\n      <td>1595884623</td>\n      <td>136</td>\n      <td>surprise az</td>\n    </tr>\n    <tr>\n      <th>61578</th>\n      <td>train_landmarks/1997878546.parquet</td>\n      <td>1997878546</td>\n      <td>711000266</td>\n      <td>161</td>\n      <td>surprise az</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"train.query('phrase == \"surprise az\"')[\"sequence_id\"].nunique()","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:03.798452Z","iopub.execute_input":"2023-07-31T11:49:03.79896Z","iopub.status.idle":"2023-07-31T11:49:03.815432Z","shell.execute_reply.started":"2023-07-31T11:49:03.79892Z","shell.execute_reply":"2023-07-31T11:49:03.814329Z"},"trusted":true},"execution_count":13,"outputs":[{"execution_count":13,"output_type":"execute_result","data":{"text/plain":"17"},"metadata":{}}]},{"cell_type":"markdown","source":"There are 17 unique sequence IDs for surprise phrase\nChoose any sequence ID and load its path(surprise), whose parquet file we will use afterwards","metadata":{}},{"cell_type":"code","source":"surprise = train.query('phrase == \"surprise az\"')[\"path\"].values[0]\nsurprised = pd.read_parquet(f\"{BASE_DIR}{surprise}\")","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:03.817046Z","iopub.execute_input":"2023-07-31T11:49:03.81745Z","iopub.status.idle":"2023-07-31T11:49:13.56057Z","shell.execute_reply.started":"2023-07-31T11:49:03.817417Z","shell.execute_reply":"2023-07-31T11:49:13.559484Z"},"trusted":true},"execution_count":14,"outputs":[]},{"cell_type":"code","source":"surprised","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:13.562048Z","iopub.execute_input":"2023-07-31T11:49:13.562413Z","iopub.status.idle":"2023-07-31T11:49:13.617311Z","shell.execute_reply.started":"2023-07-31T11:49:13.56238Z","shell.execute_reply":"2023-07-31T11:49:13.616246Z"},"trusted":true},"execution_count":15,"outputs":[{"execution_count":15,"output_type":"execute_result","data":{"text/plain":"             frame  x_face_0  x_face_1  x_face_2  x_face_3  x_face_4  \\\nsequence_id                                                            \n892546335        0  0.558532  0.544893  0.550765  0.531709  0.542882   \n892546335        1  0.558485  0.538496  0.546902  0.526788  0.536074   \n892546335        2  0.559387  0.538431  0.547265  0.526393  0.535808   \n892546335        3  0.557837  0.541629  0.549719  0.527716  0.538818   \n892546335        4  0.553872  0.537255  0.545412  0.522412  0.534153   \n...            ...       ...       ...       ...       ...       ...   \n926078741      167  0.666573  0.680770  0.679185  0.663492  0.680639   \n926078741      168  0.662258  0.676808  0.675712  0.659671  0.676574   \n926078741      169  0.661971  0.670780  0.670854  0.655241  0.670645   \n926078741      170  0.660110  0.664442  0.664654  0.648924  0.664258   \n926078741      171  0.655350  0.660850  0.660410  0.644145  0.660438   \n\n             x_face_5  x_face_6  x_face_7  x_face_8  ...  z_right_hand_11  \\\nsequence_id                                          ...                    \n892546335    0.542395  0.543382  0.461938  0.542168  ...        -0.025242   \n892546335    0.535973  0.538563  0.463473  0.537398  ...              NaN   \n892546335    0.535540  0.537791  0.468848  0.536576  ...        -0.118818   \n892546335    0.537770  0.537678  0.463155  0.535218  ...        -0.129440   \n892546335    0.532779  0.531839  0.458245  0.528752  ...              NaN   \n...               ...       ...       ...       ...  ...              ...   \n926078741    0.679611  0.676069  0.551874  0.673817  ...        -0.334243   \n926078741    0.675623  0.672584  0.550114  0.670699  ...              NaN   \n926078741    0.670540  0.669942  0.547087  0.669080  ...        -0.413789   \n926078741    0.664099  0.663613  0.542146  0.662831  ...        -0.316694   \n926078741    0.659709  0.657623  0.536247  0.655869  ...        -0.267454   \n\n             z_right_hand_12  z_right_hand_13  z_right_hand_14  \\\nsequence_id                                                      \n892546335          -0.037157        -0.016177        -0.034248   \n892546335                NaN              NaN              NaN   \n892546335          -0.137097        -0.086207        -0.124947   \n892546335          -0.154642        -0.102356        -0.143587   \n892546335                NaN              NaN              NaN   \n...                      ...              ...              ...   \n926078741          -0.392523        -0.163864        -0.238234   \n926078741                NaN              NaN              NaN   \n926078741          -0.489348        -0.185839        -0.294575   \n926078741          -0.364578        -0.173660        -0.243761   \n926078741          -0.321842        -0.112076        -0.172052   \n\n             z_right_hand_15  z_right_hand_16  z_right_hand_17  \\\nsequence_id                                                      \n892546335          -0.046090        -0.051801        -0.047187   \n892546335                NaN              NaN              NaN   \n892546335          -0.141636        -0.152644        -0.121944   \n892546335          -0.172341        -0.192996        -0.147066   \n892546335                NaN              NaN              NaN   \n...                      ...              ...              ...   \n926078741          -0.311453        -0.362199        -0.159862   \n926078741                NaN              NaN              NaN   \n926078741          -0.395767        -0.459715        -0.202480   \n926078741          -0.303576        -0.345224        -0.176801   \n926078741          -0.238773        -0.284961        -0.103608   \n\n             z_right_hand_18  z_right_hand_19  z_right_hand_20  \nsequence_id                                                     \n892546335          -0.061533        -0.066047        -0.067060  \n892546335                NaN              NaN              NaN  \n892546335          -0.153051        -0.164828        -0.173849  \n892546335          -0.180508        -0.197671        -0.212346  \n892546335                NaN              NaN              NaN  \n...                      ...              ...              ...  \n926078741          -0.223101        -0.269810        -0.305507  \n926078741                NaN              NaN              NaN  \n926078741          -0.280212        -0.346813        -0.399406  \n926078741          -0.239134        -0.279785        -0.310076  \n926078741          -0.149414        -0.188530        -0.219580  \n\n[159858 rows x 1630 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>frame</th>\n      <th>x_face_0</th>\n      <th>x_face_1</th>\n      <th>x_face_2</th>\n      <th>x_face_3</th>\n      <th>x_face_4</th>\n      <th>x_face_5</th>\n      <th>x_face_6</th>\n      <th>x_face_7</th>\n      <th>x_face_8</th>\n      <th>...</th>\n      <th>z_right_hand_11</th>\n      <th>z_right_hand_12</th>\n      <th>z_right_hand_13</th>\n      <th>z_right_hand_14</th>\n      <th>z_right_hand_15</th>\n      <th>z_right_hand_16</th>\n      <th>z_right_hand_17</th>\n      <th>z_right_hand_18</th>\n      <th>z_right_hand_19</th>\n      <th>z_right_hand_20</th>\n    </tr>\n    <tr>\n      <th>sequence_id</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>892546335</th>\n      <td>0</td>\n      <td>0.558532</td>\n      <td>0.544893</td>\n      <td>0.550765</td>\n      <td>0.531709</td>\n      <td>0.542882</td>\n      <td>0.542395</td>\n      <td>0.543382</td>\n      <td>0.461938</td>\n      <td>0.542168</td>\n      <td>...</td>\n      <td>-0.025242</td>\n      <td>-0.037157</td>\n      <td>-0.016177</td>\n      <td>-0.034248</td>\n      <td>-0.046090</td>\n      <td>-0.051801</td>\n      <td>-0.047187</td>\n      <td>-0.061533</td>\n      <td>-0.066047</td>\n      <td>-0.067060</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>1</td>\n      <td>0.558485</td>\n      <td>0.538496</td>\n      <td>0.546902</td>\n      <td>0.526788</td>\n      <td>0.536074</td>\n      <td>0.535973</td>\n      <td>0.538563</td>\n      <td>0.463473</td>\n      <td>0.537398</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>2</td>\n      <td>0.559387</td>\n      <td>0.538431</td>\n      <td>0.547265</td>\n      <td>0.526393</td>\n      <td>0.535808</td>\n      <td>0.535540</td>\n      <td>0.537791</td>\n      <td>0.468848</td>\n      <td>0.536576</td>\n      <td>...</td>\n      <td>-0.118818</td>\n      <td>-0.137097</td>\n      <td>-0.086207</td>\n      <td>-0.124947</td>\n      <td>-0.141636</td>\n      <td>-0.152644</td>\n      <td>-0.121944</td>\n      <td>-0.153051</td>\n      <td>-0.164828</td>\n      <td>-0.173849</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>3</td>\n      <td>0.557837</td>\n      <td>0.541629</td>\n      <td>0.549719</td>\n      <td>0.527716</td>\n      <td>0.538818</td>\n      <td>0.537770</td>\n      <td>0.537678</td>\n      <td>0.463155</td>\n      <td>0.535218</td>\n      <td>...</td>\n      <td>-0.129440</td>\n      <td>-0.154642</td>\n      <td>-0.102356</td>\n      <td>-0.143587</td>\n      <td>-0.172341</td>\n      <td>-0.192996</td>\n      <td>-0.147066</td>\n      <td>-0.180508</td>\n      <td>-0.197671</td>\n      <td>-0.212346</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>4</td>\n      <td>0.553872</td>\n      <td>0.537255</td>\n      <td>0.545412</td>\n      <td>0.522412</td>\n      <td>0.534153</td>\n      <td>0.532779</td>\n      <td>0.531839</td>\n      <td>0.458245</td>\n      <td>0.528752</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>926078741</th>\n      <td>167</td>\n      <td>0.666573</td>\n      <td>0.680770</td>\n      <td>0.679185</td>\n      <td>0.663492</td>\n      <td>0.680639</td>\n      <td>0.679611</td>\n      <td>0.676069</td>\n      <td>0.551874</td>\n      <td>0.673817</td>\n      <td>...</td>\n      <td>-0.334243</td>\n      <td>-0.392523</td>\n      <td>-0.163864</td>\n      <td>-0.238234</td>\n      <td>-0.311453</td>\n      <td>-0.362199</td>\n      <td>-0.159862</td>\n      <td>-0.223101</td>\n      <td>-0.269810</td>\n      <td>-0.305507</td>\n    </tr>\n    <tr>\n      <th>926078741</th>\n      <td>168</td>\n      <td>0.662258</td>\n      <td>0.676808</td>\n      <td>0.675712</td>\n      <td>0.659671</td>\n      <td>0.676574</td>\n      <td>0.675623</td>\n      <td>0.672584</td>\n      <td>0.550114</td>\n      <td>0.670699</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>926078741</th>\n      <td>169</td>\n      <td>0.661971</td>\n      <td>0.670780</td>\n      <td>0.670854</td>\n      <td>0.655241</td>\n      <td>0.670645</td>\n      <td>0.670540</td>\n      <td>0.669942</td>\n      <td>0.547087</td>\n      <td>0.669080</td>\n      <td>...</td>\n      <td>-0.413789</td>\n      <td>-0.489348</td>\n      <td>-0.185839</td>\n      <td>-0.294575</td>\n      <td>-0.395767</td>\n      <td>-0.459715</td>\n      <td>-0.202480</td>\n      <td>-0.280212</td>\n      <td>-0.346813</td>\n      <td>-0.399406</td>\n    </tr>\n    <tr>\n      <th>926078741</th>\n      <td>170</td>\n      <td>0.660110</td>\n      <td>0.664442</td>\n      <td>0.664654</td>\n      <td>0.648924</td>\n      <td>0.664258</td>\n      <td>0.664099</td>\n      <td>0.663613</td>\n      <td>0.542146</td>\n      <td>0.662831</td>\n      <td>...</td>\n      <td>-0.316694</td>\n      <td>-0.364578</td>\n      <td>-0.173660</td>\n      <td>-0.243761</td>\n      <td>-0.303576</td>\n      <td>-0.345224</td>\n      <td>-0.176801</td>\n      <td>-0.239134</td>\n      <td>-0.279785</td>\n      <td>-0.310076</td>\n    </tr>\n    <tr>\n      <th>926078741</th>\n      <td>171</td>\n      <td>0.655350</td>\n      <td>0.660850</td>\n      <td>0.660410</td>\n      <td>0.644145</td>\n      <td>0.660438</td>\n      <td>0.659709</td>\n      <td>0.657623</td>\n      <td>0.536247</td>\n      <td>0.655869</td>\n      <td>...</td>\n      <td>-0.267454</td>\n      <td>-0.321842</td>\n      <td>-0.112076</td>\n      <td>-0.172052</td>\n      <td>-0.238773</td>\n      <td>-0.284961</td>\n      <td>-0.103608</td>\n      <td>-0.149414</td>\n      <td>-0.188530</td>\n      <td>-0.219580</td>\n    </tr>\n  </tbody>\n</table>\n<p>159858 rows × 1630 columns</p>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"surprised.index.nunique()","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:13.619111Z","iopub.execute_input":"2023-07-31T11:49:13.61979Z","iopub.status.idle":"2023-07-31T11:49:13.630534Z","shell.execute_reply.started":"2023-07-31T11:49:13.619753Z","shell.execute_reply":"2023-07-31T11:49:13.629405Z"},"trusted":true},"execution_count":16,"outputs":[{"execution_count":16,"output_type":"execute_result","data":{"text/plain":"999"},"metadata":{}}]},{"cell_type":"markdown","source":"There are total of 999 unique sequence Ids for first parquet file of surprised phrase","metadata":{}},{"cell_type":"code","source":"selected_id = surprised.index.values[10]\nprint(selected_id)","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:13.632182Z","iopub.execute_input":"2023-07-31T11:49:13.633045Z","iopub.status.idle":"2023-07-31T11:49:13.638371Z","shell.execute_reply.started":"2023-07-31T11:49:13.633013Z","shell.execute_reply":"2023-07-31T11:49:13.637261Z"},"trusted":true},"execution_count":17,"outputs":[{"name":"stdout","text":"892546335\n","output_type":"stream"}]},{"cell_type":"markdown","source":"let's see how many instances are there for this sequence id","metadata":{}},{"cell_type":"code","source":"selected_id_df = surprised[surprised.index == selected_id]\nselected_id_df","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:13.640024Z","iopub.execute_input":"2023-07-31T11:49:13.64065Z","iopub.status.idle":"2023-07-31T11:49:13.682468Z","shell.execute_reply.started":"2023-07-31T11:49:13.640618Z","shell.execute_reply":"2023-07-31T11:49:13.681411Z"},"trusted":true},"execution_count":18,"outputs":[{"execution_count":18,"output_type":"execute_result","data":{"text/plain":"             frame  x_face_0  x_face_1  x_face_2  x_face_3  x_face_4  \\\nsequence_id                                                            \n892546335        0  0.558532  0.544893  0.550765  0.531709  0.542882   \n892546335        1  0.558485  0.538496  0.546902  0.526788  0.536074   \n892546335        2  0.559387  0.538431  0.547265  0.526393  0.535808   \n892546335        3  0.557837  0.541629  0.549719  0.527716  0.538818   \n892546335        4  0.553872  0.537255  0.545412  0.522412  0.534153   \n...            ...       ...       ...       ...       ...       ...   \n892546335      181  0.578249  0.560990  0.565916  0.550919  0.560023   \n892546335      182  0.570036  0.560048  0.565438  0.550385  0.559063   \n892546335      183  0.572381  0.560202  0.565597  0.550710  0.559303   \n892546335      184  0.573491  0.561402  0.566634  0.551771  0.560563   \n892546335      185  0.571908  0.562277  0.567263  0.552012  0.561251   \n\n             x_face_5  x_face_6  x_face_7  x_face_8  ...  z_right_hand_11  \\\nsequence_id                                          ...                    \n892546335    0.542395  0.543382  0.461938  0.542168  ...        -0.025242   \n892546335    0.535973  0.538563  0.463473  0.537398  ...              NaN   \n892546335    0.535540  0.537791  0.468848  0.536576  ...        -0.118818   \n892546335    0.537770  0.537678  0.463155  0.535218  ...        -0.129440   \n892546335    0.532779  0.531839  0.458245  0.528752  ...              NaN   \n...               ...       ...       ...       ...  ...              ...   \n892546335    0.560634  0.563948  0.481150  0.564354  ...              NaN   \n892546335    0.559858  0.563741  0.481256  0.564522  ...              NaN   \n892546335    0.560203  0.564364  0.482341  0.565159  ...        -0.039151   \n892546335    0.561471  0.565530  0.483249  0.566310  ...        -0.069106   \n892546335    0.561883  0.565316  0.483737  0.565634  ...        -0.155539   \n\n             z_right_hand_12  z_right_hand_13  z_right_hand_14  \\\nsequence_id                                                      \n892546335          -0.037157        -0.016177        -0.034248   \n892546335                NaN              NaN              NaN   \n892546335          -0.137097        -0.086207        -0.124947   \n892546335          -0.154642        -0.102356        -0.143587   \n892546335                NaN              NaN              NaN   \n...                      ...              ...              ...   \n892546335                NaN              NaN              NaN   \n892546335                NaN              NaN              NaN   \n892546335          -0.051417        -0.003684        -0.021194   \n892546335          -0.078822        -0.020741        -0.059064   \n892546335          -0.176264        -0.082482        -0.130140   \n\n             z_right_hand_15  z_right_hand_16  z_right_hand_17  \\\nsequence_id                                                      \n892546335          -0.046090        -0.051801        -0.047187   \n892546335                NaN              NaN              NaN   \n892546335          -0.141636        -0.152644        -0.121944   \n892546335          -0.172341        -0.192996        -0.147066   \n892546335                NaN              NaN              NaN   \n...                      ...              ...              ...   \n892546335                NaN              NaN              NaN   \n892546335                NaN              NaN              NaN   \n892546335          -0.030969        -0.034359        -0.018091   \n892546335          -0.077334        -0.079288        -0.037034   \n892546335          -0.159636        -0.176056        -0.093759   \n\n             z_right_hand_18  z_right_hand_19  z_right_hand_20  \nsequence_id                                                     \n892546335          -0.061533        -0.066047        -0.067060  \n892546335                NaN              NaN              NaN  \n892546335          -0.153051        -0.164828        -0.173849  \n892546335          -0.180508        -0.197671        -0.212346  \n892546335                NaN              NaN              NaN  \n...                      ...              ...              ...  \n892546335                NaN              NaN              NaN  \n892546335                NaN              NaN              NaN  \n892546335          -0.025781        -0.022853        -0.018749  \n892546335          -0.057725        -0.064785        -0.066444  \n892546335          -0.134799        -0.153789        -0.164360  \n\n[186 rows x 1630 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>frame</th>\n      <th>x_face_0</th>\n      <th>x_face_1</th>\n      <th>x_face_2</th>\n      <th>x_face_3</th>\n      <th>x_face_4</th>\n      <th>x_face_5</th>\n      <th>x_face_6</th>\n      <th>x_face_7</th>\n      <th>x_face_8</th>\n      <th>...</th>\n      <th>z_right_hand_11</th>\n      <th>z_right_hand_12</th>\n      <th>z_right_hand_13</th>\n      <th>z_right_hand_14</th>\n      <th>z_right_hand_15</th>\n      <th>z_right_hand_16</th>\n      <th>z_right_hand_17</th>\n      <th>z_right_hand_18</th>\n      <th>z_right_hand_19</th>\n      <th>z_right_hand_20</th>\n    </tr>\n    <tr>\n      <th>sequence_id</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>892546335</th>\n      <td>0</td>\n      <td>0.558532</td>\n      <td>0.544893</td>\n      <td>0.550765</td>\n      <td>0.531709</td>\n      <td>0.542882</td>\n      <td>0.542395</td>\n      <td>0.543382</td>\n      <td>0.461938</td>\n      <td>0.542168</td>\n      <td>...</td>\n      <td>-0.025242</td>\n      <td>-0.037157</td>\n      <td>-0.016177</td>\n      <td>-0.034248</td>\n      <td>-0.046090</td>\n      <td>-0.051801</td>\n      <td>-0.047187</td>\n      <td>-0.061533</td>\n      <td>-0.066047</td>\n      <td>-0.067060</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>1</td>\n      <td>0.558485</td>\n      <td>0.538496</td>\n      <td>0.546902</td>\n      <td>0.526788</td>\n      <td>0.536074</td>\n      <td>0.535973</td>\n      <td>0.538563</td>\n      <td>0.463473</td>\n      <td>0.537398</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>2</td>\n      <td>0.559387</td>\n      <td>0.538431</td>\n      <td>0.547265</td>\n      <td>0.526393</td>\n      <td>0.535808</td>\n      <td>0.535540</td>\n      <td>0.537791</td>\n      <td>0.468848</td>\n      <td>0.536576</td>\n      <td>...</td>\n      <td>-0.118818</td>\n      <td>-0.137097</td>\n      <td>-0.086207</td>\n      <td>-0.124947</td>\n      <td>-0.141636</td>\n      <td>-0.152644</td>\n      <td>-0.121944</td>\n      <td>-0.153051</td>\n      <td>-0.164828</td>\n      <td>-0.173849</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>3</td>\n      <td>0.557837</td>\n      <td>0.541629</td>\n      <td>0.549719</td>\n      <td>0.527716</td>\n      <td>0.538818</td>\n      <td>0.537770</td>\n      <td>0.537678</td>\n      <td>0.463155</td>\n      <td>0.535218</td>\n      <td>...</td>\n      <td>-0.129440</td>\n      <td>-0.154642</td>\n      <td>-0.102356</td>\n      <td>-0.143587</td>\n      <td>-0.172341</td>\n      <td>-0.192996</td>\n      <td>-0.147066</td>\n      <td>-0.180508</td>\n      <td>-0.197671</td>\n      <td>-0.212346</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>4</td>\n      <td>0.553872</td>\n      <td>0.537255</td>\n      <td>0.545412</td>\n      <td>0.522412</td>\n      <td>0.534153</td>\n      <td>0.532779</td>\n      <td>0.531839</td>\n      <td>0.458245</td>\n      <td>0.528752</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>181</td>\n      <td>0.578249</td>\n      <td>0.560990</td>\n      <td>0.565916</td>\n      <td>0.550919</td>\n      <td>0.560023</td>\n      <td>0.560634</td>\n      <td>0.563948</td>\n      <td>0.481150</td>\n      <td>0.564354</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>182</td>\n      <td>0.570036</td>\n      <td>0.560048</td>\n      <td>0.565438</td>\n      <td>0.550385</td>\n      <td>0.559063</td>\n      <td>0.559858</td>\n      <td>0.563741</td>\n      <td>0.481256</td>\n      <td>0.564522</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>183</td>\n      <td>0.572381</td>\n      <td>0.560202</td>\n      <td>0.565597</td>\n      <td>0.550710</td>\n      <td>0.559303</td>\n      <td>0.560203</td>\n      <td>0.564364</td>\n      <td>0.482341</td>\n      <td>0.565159</td>\n      <td>...</td>\n      <td>-0.039151</td>\n      <td>-0.051417</td>\n      <td>-0.003684</td>\n      <td>-0.021194</td>\n      <td>-0.030969</td>\n      <td>-0.034359</td>\n      <td>-0.018091</td>\n      <td>-0.025781</td>\n      <td>-0.022853</td>\n      <td>-0.018749</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>184</td>\n      <td>0.573491</td>\n      <td>0.561402</td>\n      <td>0.566634</td>\n      <td>0.551771</td>\n      <td>0.560563</td>\n      <td>0.561471</td>\n      <td>0.565530</td>\n      <td>0.483249</td>\n      <td>0.566310</td>\n      <td>...</td>\n      <td>-0.069106</td>\n      <td>-0.078822</td>\n      <td>-0.020741</td>\n      <td>-0.059064</td>\n      <td>-0.077334</td>\n      <td>-0.079288</td>\n      <td>-0.037034</td>\n      <td>-0.057725</td>\n      <td>-0.064785</td>\n      <td>-0.066444</td>\n    </tr>\n    <tr>\n      <th>892546335</th>\n      <td>185</td>\n      <td>0.571908</td>\n      <td>0.562277</td>\n      <td>0.567263</td>\n      <td>0.552012</td>\n      <td>0.561251</td>\n      <td>0.561883</td>\n      <td>0.565316</td>\n      <td>0.483737</td>\n      <td>0.565634</td>\n      <td>...</td>\n      <td>-0.155539</td>\n      <td>-0.176264</td>\n      <td>-0.082482</td>\n      <td>-0.130140</td>\n      <td>-0.159636</td>\n      <td>-0.176056</td>\n      <td>-0.093759</td>\n      <td>-0.134799</td>\n      <td>-0.153789</td>\n      <td>-0.164360</td>\n    </tr>\n  </tbody>\n</table>\n<p>186 rows × 1630 columns</p>\n</div>"},"metadata":{}}]},{"cell_type":"markdown","source":"There are total of 186 instances for the selected sequence Id","metadata":{}},{"cell_type":"markdown","source":"Create a function which will seperate all the columns for loaded parquet file along three axes - x, y, z","metadata":{}},{"cell_type":"code","source":"def x_y_z(columns):\n    x = [col for col in columns if col.startswith(\"x\")]\n    y = [col for col in columns if col.startswith(\"y\")]\n    z = [col for col in columns if col.startswith(\"z\")]\n    return x, y, z","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:13.683938Z","iopub.execute_input":"2023-07-31T11:49:13.684536Z","iopub.status.idle":"2023-07-31T11:49:13.691541Z","shell.execute_reply.started":"2023-07-31T11:49:13.684502Z","shell.execute_reply":"2023-07-31T11:49:13.690292Z"},"trusted":true},"execution_count":19,"outputs":[]},{"cell_type":"markdown","source":"Creating a function which will store types of landmarks present for that id","metadata":{}},{"cell_type":"code","source":"def type_of_landmark(example_landmark):\n    body_parts = set()\n    for col in example_landmark.columns:\n        parts = col.split(\"_\")\n        if len(parts) >= 2:\n            if parts[1] == \"right\":\n                body_parts.add(\"right_hand\")\n            elif parts[1] == \"left\":\n                body_parts.add(\"left_hand\")\n            else:\n                body_parts.add(parts[1])\n    return body_parts","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:13.693463Z","iopub.execute_input":"2023-07-31T11:49:13.693895Z","iopub.status.idle":"2023-07-31T11:49:13.704302Z","shell.execute_reply.started":"2023-07-31T11:49:13.693859Z","shell.execute_reply":"2023-07-31T11:49:13.703105Z"},"trusted":true},"execution_count":20,"outputs":[]},{"cell_type":"code","source":"from colorama import Style, Fore\n\nblk = Style.BRIGHT + Fore.BLACK\nred = Style.BRIGHT + Fore.RED\nblu = Style.BRIGHT + Fore.BLUE\ncyan = Style.BRIGHT + Fore.CYAN\ngreen = Style.BRIGHT + Fore.GREEN\nres = Style.RESET_ALL","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:13.706233Z","iopub.execute_input":"2023-07-31T11:49:13.708032Z","iopub.status.idle":"2023-07-31T11:49:13.716834Z","shell.execute_reply.started":"2023-07-31T11:49:13.707994Z","shell.execute_reply":"2023-07-31T11:49:13.714811Z"},"trusted":true},"execution_count":21,"outputs":[]},{"cell_type":"code","source":"unique_frames = selected_id_df[\"frame\"].nunique()\n# type of landmarks/body parts = [face/pose/right hand/left hand]\ntype_landmark_train = type_of_landmark(selected_id_df)\n\n# seperate columns according to landmarks\nface_train = [col for col in selected_id_df.columns if \"face\" in col]\nright_hand_train = [col for col in selected_id_df.columns if \"right_hand\" in col]\nleft_hand_train = [col for col in selected_id_df.columns if \"left_hand\" in col]\npose_train = [col for col in selected_id_df.columns if \"pose\" in col]\n\n# use the function created earlier to distribute along axes\nx_face_train, y_face_train, z_face_train = x_y_z(face_train)\nx_right_hand, y_right_hand, z_right_hand = x_y_z(right_hand_train)\nx_left_hand, y_left_hand, z_left_hand = x_y_z(left_hand_train)\nx_pose, y_pose, z_pose = x_y_z(pose_train)\n\n# Summary\nprint(f'{cyan}{\"*\"*30} Training Data {\"*\"*30}')\nprint(f\"{blk}Selected Sequence ID: {red}{selected_id}\")\nprint(f\"{blk}Unique Frames: {red} {unique_frames}\")\nprint(\n    f\"{blk}Selected example has total {red}{len(type_landmark_train)}{blk} landmards and they are{red}{type_landmark_train}\"\n)\nprint(f\"{blk}{red}\")\nprint(f'{green}{\"*\"*20}FACE{\"*\"*20}')\nprint(f\"{blk}Total Keypoints: {red}{len(face_train)}\")\nprint(f\"{blk}Keypoints in X: {red}{len(x_face_train)}\")\nprint(f\"{blk}Keypoints in Y: {red}{len(y_face_train)}\")\nprint(f\"{blk}Keypoints in Z: {red}{len(z_face_train)}\")\n\nprint(f'{green}{\"*\"*20}RIGHT HAND{\"*\"*20}')\nprint(f\"{blk}Total Keypoints: {red}{len(right_hand_train)}\")\nprint(f\"{blk}Keypoints in X: {red}{len(x_right_hand)}\")\nprint(f\"{blk}Keypoints in Y: {red}{len(y_right_hand)}\")\nprint(f\"{blk}Keypoints in Z: {red}{len(z_right_hand)}\")\n\nprint(f'{green}{\"*\"*20}LEFT HAND{\"*\"*20}')\nprint(f\"{blk}Total Keypoints: {red}{len(left_hand_train)}\")\nprint(f\"{blk}Keypoints in X: {red}{len(x_left_hand)}\")\nprint(f\"{blk}Keypoints in Y: {red}{len(y_left_hand)}\")\nprint(f\"{blk}Keypoints in Z: {red}{len(z_left_hand)}\")\n\nprint(f'{green}{\"*\"*20}POSE{\"*\"*20}')\nprint(f\"{blk}Total Keypoints: {red}{len(pose_train)}\")\nprint(f\"{blk}Keypoints in X: {red}{len(x_pose)}\")\nprint(f\"{blk}Keypoints in Y: {red}{len(y_pose)}\")\nprint(f\"{blk}Keypoints in Z: {red}{len(z_pose)}\")","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:13.720062Z","iopub.execute_input":"2023-07-31T11:49:13.720523Z","iopub.status.idle":"2023-07-31T11:49:13.742097Z","shell.execute_reply.started":"2023-07-31T11:49:13.72049Z","shell.execute_reply":"2023-07-31T11:49:13.740993Z"},"trusted":true},"execution_count":22,"outputs":[{"name":"stdout","text":"\u001b[1m\u001b[36m****************************** Training Data ******************************\n\u001b[1m\u001b[30mSelected Sequence ID: \u001b[1m\u001b[31m892546335\n\u001b[1m\u001b[30mUnique Frames: \u001b[1m\u001b[31m 186\n\u001b[1m\u001b[30mSelected example has total \u001b[1m\u001b[31m4\u001b[1m\u001b[30m landmards and they are\u001b[1m\u001b[31m{'left_hand', 'pose', 'right_hand', 'face'}\n\u001b[1m\u001b[30m\u001b[1m\u001b[31m\n\u001b[1m\u001b[32m********************FACE********************\n\u001b[1m\u001b[30mTotal Keypoints: \u001b[1m\u001b[31m1404\n\u001b[1m\u001b[30mKeypoints in X: \u001b[1m\u001b[31m468\n\u001b[1m\u001b[30mKeypoints in Y: \u001b[1m\u001b[31m468\n\u001b[1m\u001b[30mKeypoints in Z: \u001b[1m\u001b[31m468\n\u001b[1m\u001b[32m********************RIGHT HAND********************\n\u001b[1m\u001b[30mTotal Keypoints: \u001b[1m\u001b[31m63\n\u001b[1m\u001b[30mKeypoints in X: \u001b[1m\u001b[31m21\n\u001b[1m\u001b[30mKeypoints in Y: \u001b[1m\u001b[31m21\n\u001b[1m\u001b[30mKeypoints in Z: \u001b[1m\u001b[31m21\n\u001b[1m\u001b[32m********************LEFT HAND********************\n\u001b[1m\u001b[30mTotal Keypoints: \u001b[1m\u001b[31m63\n\u001b[1m\u001b[30mKeypoints in X: \u001b[1m\u001b[31m21\n\u001b[1m\u001b[30mKeypoints in Y: \u001b[1m\u001b[31m21\n\u001b[1m\u001b[30mKeypoints in Z: \u001b[1m\u001b[31m21\n\u001b[1m\u001b[32m********************POSE********************\n\u001b[1m\u001b[30mTotal Keypoints: \u001b[1m\u001b[31m99\n\u001b[1m\u001b[30mKeypoints in X: \u001b[1m\u001b[31m33\n\u001b[1m\u001b[30mKeypoints in Y: \u001b[1m\u001b[31m33\n\u001b[1m\u001b[30mKeypoints in Z: \u001b[1m\u001b[31m33\n","output_type":"stream"}]},{"cell_type":"markdown","source":"# CREATE METADATA FOR THE TRAINING DATASET","metadata":{}},{"cell_type":"code","source":" xyz_meta = example_landmark.agg(\n        {\n            \"x_face_0\":[\"min\", \"max\", \"mean\"],\n            \"x_face_1\":[\"min\", \"max\", \"mean\"], \n            \"x_face_2\":[\"min\", \"max\", \"mean\"], \n            \"x_face_3\":[\"min\", \"max\", \"mean\"], \n            \"y_left_hand_0\":[\"min\", \"max\", \"mean\"], \n            \"y_left_hand_1\":[\"min\", \"max\", \"mean\"], \n            \"y_left_hand_2\":[\"min\", \"max\", \"mean\"], \n            \"y_left_hand_3\":[\"min\", \"max\", \"mean\"], \n            \"z_right_hand_0\":[\"min\", \"max\", \"mean\"],\n            \"z_right_hand_1\":[\"min\", \"max\", \"mean\"], \n            \"z_right_hand_2\":[\"min\", \"max\", \"mean\"], \n            \"z_right_hand_3\":[\"min\", \"max\", \"mean\"],\n        }\n    )","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:13.743551Z","iopub.execute_input":"2023-07-31T11:49:13.744697Z","iopub.status.idle":"2023-07-31T11:49:13.795068Z","shell.execute_reply.started":"2023-07-31T11:49:13.744663Z","shell.execute_reply":"2023-07-31T11:49:13.79391Z"},"trusted":true},"execution_count":23,"outputs":[]},{"cell_type":"code","source":"N_PARQUETS_TO_READ = 100\nimport pandas as pd\nfrom tqdm import tqdm\n\nBASE_DIR = '../input/asl-fingerspelling/'\ntrain = pd.read_csv('/kaggle/input/asl-fingerspelling/train.csv')\n\ncombined_meta = {}\nfor i, d in tqdm(train.iterrows(), total=len(train)):\n    file_path = d[\"path\"]\n    example_landmark = pd.read_parquet(f\"{BASE_DIR}/{file_path}\")\n    meta = example_landmark.dropna(subset=['x_face_0', 'x_face_1', 'x_face_2', 'x_face_3', 'x_face_4',\n       'x_face_5', 'x_face_6', 'x_face_7', 'x_face_8',\n       'z_right_hand_11', 'z_right_hand_12', 'z_right_hand_13',\n       'z_right_hand_14', 'z_right_hand_15', 'z_right_hand_16',\n       'z_right_hand_17', 'z_right_hand_18', 'z_right_hand_19',\n       'z_right_hand_20'])[\"frame\"].value_counts().to_dict()\n    meta[\"frames\"] = example_landmark[\"frame\"].nunique()\n    \n    xyz_meta = (\n        example_landmark.agg(\n        {\n            \"x_face_0\":[\"min\", \"max\", \"mean\"],\n            \"x_face_1\":[\"min\", \"max\", \"mean\"], \n            \"x_face_2\":[\"min\", \"max\", \"mean\"], \n            \"x_face_3\":[\"min\", \"max\", \"mean\"], \n            \"y_left_hand_0\":[\"min\", \"max\", \"mean\"], \n            \"y_left_hand_1\":[\"min\", \"max\", \"mean\"], \n            \"y_left_hand_2\":[\"min\", \"max\", \"mean\"], \n            \"y_left_hand_3\":[\"min\", \"max\", \"mean\"], \n            \"z_right_hand_0\":[\"min\", \"max\", \"mean\"],\n            \"z_right_hand_1\":[\"min\", \"max\", \"mean\"], \n            \"z_right_hand_2\":[\"min\", \"max\", \"mean\"], \n            \"z_right_hand_3\":[\"min\", \"max\", \"mean\"],\n        }\n    )\n    .unstack().to_dict()\n    )\n    \n    for key in xyz_meta.keys():\n        new_key = key[0] + \"_\" + key[1]\n        meta[new_key] = xyz_meta[key]\n    \n    combined_meta[file_path] = meta\n    \n    if i >= N_PARQUETS_TO_READ:\n        break","metadata":{"execution":{"iopub.status.busy":"2023-07-31T11:49:13.797038Z","iopub.execute_input":"2023-07-31T11:49:13.79749Z"},"trusted":true},"execution_count":null,"outputs":[{"name":"stderr","text":"  0%|          | 144/67208 [10:23<74:58:25,  4.02s/it]","output_type":"stream"}]},{"cell_type":"code","source":"xyz_meta","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\ncombined_meta = {}\ntrain = pd.read_csv('/kaggle/input/asl-fingerspelling/train.csv')\ntrain_with_meta = train.merge(\n    pd.DataFrame(combined_meta).T.reset_index().rename(columns={\"index\": \"path\"}),\n    how=\"left\",\n)\ntrain_with_meta.to_parquet(\"train_with_meta.parquet\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"What are the most frequent types of landmarks provided?\n- face has a lot more datapoints because mediapipe provides 468 3D datapoints per frame.","metadata":{}},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n# Exclude columns with mixed data types from sorting\ndesired_columns = ['path', 'file_id', 'sequence_id', 'participant_id', 'phrase']\nnumerical_columns = [col for col in desired_columns if train_with_meta[col].dtype != object]\n# Plot the graph\ntrain_with_meta[numerical_columns].sum().sort_values().plot(kind=\"barh\", title=\"Sum of Rows by Landmark Type\")\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\n# Define the custom comparison function\ndef custom_comparison(x):\n    if pd.api.types.is_numeric_dtype(x):\n        return x > 0\n    else:\n        return x\n# Perform the comparison\ncomparison_result = train_with_meta.query('index < 1000').fillna(0)[\n    [\"path\", \"file_id\", \"sequence_id\", \"participant_id\", \"phrase\"]\n].apply(custom_comparison)\nmean_result = comparison_result.mean().plot(kind = 'barh', title = 'Percent of Frame/keypoints with Data')\nprint(mean_result)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"example_landmark.dropna(subset=['x_face_0', 'x_face_1', 'x_face_2', 'x_face_3', 'x_face_4',\n       'x_face_5', 'x_face_6', 'x_face_7', 'x_face_8',\n       \n       'z_right_hand_11', 'z_right_hand_12', 'z_right_hand_13',\n       'z_right_hand_14', 'z_right_hand_15', 'z_right_hand_16',\n       'z_right_hand_17', 'z_right_hand_18', 'z_right_hand_19',\n       'z_right_hand_20'])[\"frame\"].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(example_landmark.columns)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pattern = '^(x_|y_|z_)'\nfiltered_columns = example_landmark.filter(regex=pattern)\nexample_landmark.dropna(subset=filtered_columns.columns)[\"frame\"].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"columns = [\"file_id\", \"sequence_id\", \"participant_id\", \"phrase\"]\ntrain_with_meta.dropna(subset=[\"path\"])[columns].apply(pd.to_numeric, errors='coerce') > 0","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Every parquet file has at least some datapoints for all four types of landmarks:**\n\n- Face, pose, left hand and right hand.","metadata":{}},{"cell_type":"markdown","source":"# Check one example ","metadata":{}},{"cell_type":"code","source":"import pandas as pd \nBASE_DIR = '../input/asl-fingerspelling/'\ntrain = pd.read_csv('/kaggle/input/asl-fingerspelling/train.csv')\nexample_fn = train.query('phrase == \"surprise az\"')[\"path\"].values[0]\nexample_landmark = pd.read_parquet(f\"{BASE_DIR}/{example_fn}\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"example_landmark[\"no_xyz\"] = example_landmark['x_face_0'].isna()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"example_landmark.groupby(\"frame\")[\"no_xyz\"].sum()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"example_landmark.groupby(\"frame\")[\"no_xyz\"].sum().plot(\n    title=\"missing xyz per frame\", kind=\"bar\"\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"example_landmark[\"frame\"].median()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 3D plot of Landmarks from \"surprise_az\" example\n\nPick frame 578 because we have no missing xyz data","metadata":{}},{"cell_type":"code","source":"example_frame = example_landmark.query(\"frame == 578\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import plotly.express as px\nimport pandas as pd\ndf = pd.DataFrame({\n    'frame': [578, 578, 578, 578, 578],\n    'x_face': [0.574436, 0.620399, 0.550710, 0.615361, 0.473677],\n    'y_face': [0.560474, 0.604428, 0.539382, 0.603240, 0.468712],\n    'z_face': [0.566295, 0.609184, 0.545007, 0.609855, 0.470851],\n    'x_right_hand': [0.482442, 0.475004, 0.463145, 0.520459, 0.327291],\n    'y_right_hand': [0.563047, 0.598960, 0.537619, 0.608835, 0.478398],\n    'z_right_hand': [0.543066, -0.058136, 0.550710, 0.613422, -0.171806]\n})\n\nfig = px.scatter_3d(df, x='x_face', y='y_face', z='z_face')\nfig.show()\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Try to draw the Mediapipe's hand connections?","metadata":{}},{"cell_type":"code","source":"!pip install mediapipe --quiet","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import mediapipe as mp\nmp_hands = mp.solutions.hands\nmp_hands.HAND_CONNECTIONS","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"selected_id_df.query(\"sequence_id == @selected_id and frame == 12\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"selected_id_df.query(\"sequence_id == @selected_id and frame == 2\")[x_face_train]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"selected_id_df.query(\"sequence_id == @selected_id and frame == 2\")[x_face_train].iloc[\n    0\n].values","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(\n    selected_id_df.query(\"sequence_id == @selected_id and frame == 2\")[x_face_train]\n    .iloc[0]\n    .values\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(\n    [\n        int(col.split(\"_\")[-1])\n        for col in selected_id_df.query(\"sequence_id == @selected_id and frame == 12\")[\n            face_train\n        ].columns\n    ]\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def data_plot(seq, frame, x_col, y_col, z_col, df):\n    x = df.query(\"sequence_id == @seq and frame == @frame\")[x_col].iloc[0].values\n    y = df.query(\"sequence_id == @seq and frame == @frame\")[y_col].iloc[0].values\n    z = df.query(\"sequence_id == @seq and frame == @frame\")[z_col].iloc[0].values\n\n    landmark_idx = [\n        int(col.split(\"_\")[-1])\n        for col in df.query(\"sequence_id == @seq and frame == @frame\")[x_col].columns\n    ]\n\n    dataframe = pd.DataFrame({\"x\": x, \"y\": y, \"z\": z, \"landmark_idx\": landmark_idx})\n\n    return dataframe","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"frame = 3\nleft_hand_train = data_plot(\n    selected_id, frame, x_left_hand, y_left_hand, z_left_hand, selected_id_df\n)\nright_hand_train = data_plot(\n    selected_id, frame, x_right_hand, y_right_hand, z_right_hand, selected_id_df\n)\nface_train = data_plot(\n    selected_id, frame, x_face_train, y_face_train, z_face_train, selected_id_df\n)\npose_train = data_plot(selected_id, frame, x_pose, y_pose, z_pose, selected_id_df)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(5, 5))\nax.scatter(right_hand_train[\"x\"], right_hand_train[\"y\"])\nax.scatter(left_hand_train[\"x\"], left_hand_train[\"y\"])\nax.scatter(face_train[\"x\"], face_train[\"y\"])\nax.scatter(pose_train[\"x\"], pose_train[\"y\"])\n\n\nfor connection in mp_hands.HAND_CONNECTIONS:\n    point_a = connection[0]\n    point_b = connection[1]\n    x1, y1 = right_hand_train.query(\"landmark_idx == @point_a\")[[\"x\", \"y\"]].values[0]\n    x2, y2 = right_hand_train.query(\"landmark_idx == @point_b\")[[\"x\", \"y\"]].values[0]\n    plt.plot([x1, x2], [y1, y2], color=\"red\")\n    x3, y3 = left_hand_train.query(\"landmark_idx == @point_a\")[[\"x\", \"y\"]].values[0]\n    x4, y4 = left_hand_train.query(\"landmark_idx == @point_b\")[[\"x\", \"y\"]].values[0]\n    plt.plot([x3, x4], [y3, y4], color=\"red\")\n    x5, y5 = face_train.query(\"landmark_idx == @point_a\")[[\"x\", \"y\"]].values[0]\n    x6, y6 = face_train.query(\"landmark_idx == @point_b\")[[\"x\", \"y\"]].values[0]\n    plt.plot([x5, x6], [y5, y6], color=\"blue\")\n    x7, y7 = pose_train.query(\"landmark_idx == @point_a\")[[\"x\", \"y\"]].values[0]\n    x8, y8 = pose_train.query(\"landmark_idx == @point_b\")[[\"x\", \"y\"]].values[0]\n    plt.plot([x7, x8], [y7, y8], color=\"blue\")\n\nax.set_title(\"Surprised\")\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(5, 5))\nax.scatter(right_hand_train[\"x\"], right_hand_train[\"y\"])\nax.scatter(left_hand_train[\"x\"], left_hand_train[\"y\"])\n# ax.scatter(face_train[\"x\"], face_train[\"y\"])\n# ax.scatter(pose_train[\"x\"], pose_train[\"y\"])\n\n\nfor connection in mp_hands.HAND_CONNECTIONS:\n    point_a = connection[0]\n    point_b = connection[1]\n    x1, y1 = right_hand_train.query(\"landmark_idx == @point_a\")[[\"x\", \"y\"]].values[0]\n    x2, y2 = right_hand_train.query(\"landmark_idx == @point_b\")[[\"x\", \"y\"]].values[0]\n    plt.plot([x1, x2], [y1, y2], color=\"red\")\n    x3, y3 = left_hand_train.query(\"landmark_idx == @point_a\")[[\"x\", \"y\"]].values[0]\n    x4, y4 = left_hand_train.query(\"landmark_idx == @point_b\")[[\"x\", \"y\"]].values[0]\n    plt.plot([x3, x4], [y3, y4], color=\"red\")\n\nax.set_title(\"Surprised\")\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(5, 5))\n# ax.scatter(right_hand_train[\"x\"], right_hand_train[\"y\"])\n# ax.scatter(left_hand_train[\"x\"], left_hand_train[\"y\"])\nax.scatter(face_train[\"x\"], face_train[\"y\"])\nax.scatter(pose_train[\"x\"], pose_train[\"y\"])\n\n\nfor connection in mp_hands.HAND_CONNECTIONS:\n    point_a = connection[0]\n    point_b = connection[1]\n    x5, y5 = face_train.query(\"landmark_idx == @point_a\")[[\"x\", \"y\"]].values[0]\n    x6, y6 = face_train.query(\"landmark_idx == @point_b\")[[\"x\", \"y\"]].values[0]\n    plt.plot([x5, x6], [y5, y6], color=\"blue\")\n    x7, y7 = pose_train.query(\"landmark_idx == @point_a\")[[\"x\", \"y\"]].values[0]\n    x8, y8 = pose_train.query(\"landmark_idx == @point_b\")[[\"x\", \"y\"]].values[0]\n    plt.plot([x7, x8], [y7, y8], color=\"blue\")\n\nax.set_title(\"Surprised\")\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def map_new_to_old_style(sequence):\n    # there are 4 types of landmarks [face,pose,right_hand,left_hand]\n    types = []# list where we'll store landmarks\n    landmark_indexes = []\n    for column in list(sequence.columns)[1:544]:\n        # first column is frame which is not a landmark so counter starts from 1\n        # why 544 - because we are given that there are now 1,629 spatial coordinate columns for the x, y and z coordinates for each of the 543 landmarks.\n        parts = column.split(\"_\")\n        if len(parts) == 4:\n            # for x_left_hand_1 - there will be 4 parts and for x_pose_1 there will be 3 only\n            types.append(parts[1] + \"_\" + parts[2])\n        else:\n            types.append(parts[1])\n\n        landmark_indexes.append(int(parts[-1]))\n\n    data = {\"frame\": [], \"type\": [], \"landmark_index\": [], \"x\": [], \"y\": [], \"z\": []}\n\n    for index, row in sequence.iterrows():\n        data[\"frame\"] += [int(row.frame)] * 543\n        data[\"type\"] += types\n        data[\"landmark_index\"] += landmark_indexes\n\n        for _type, landmark_index in zip(types, landmark_indexes):\n            data[\"x\"].append(row[f\"x_{_type}_{landmark_index}\"])\n            data[\"y\"].append(row[f\"y_{_type}_{landmark_index}\"])\n            data[\"z\"].append(row[f\"z_{_type}_{landmark_index}\"])\n\n    return pd.DataFrame.from_dict(data)\n\n\ndef assign_colors(row):\n    if row == \"face\":\n        return \"red\"\n    elif \"hand\" in row:\n        return \"blue\"\n    else:\n        return \"green\"\n\n\n# specifies the plotting order\ndef assign_order(row):\n    if row.type == \"face\":\n        return row.landmark_index + 101\n    elif row.type == \"pose\":\n        return row.landmark_index + 30\n    elif row.type == \"left_hand\":\n        return row.landmark_index + 80\n    else:\n        return row.landmark_index\n\n\n# A function to visualize the landmarks in 2d\ndef visualise2d_landmarks(parquet_df, title=\"\"):\n    # we first define a list of landmark connections, which specify which landmarks are connected by a line.\n\n    # face landmarks are not connected by lines, you can also see that we have added 101 to face landmark indexs and in connections all values are below 100\n\n    connections = [  \n        [0, 1, 2, 3, 4,],\n        [0, 5, 6, 7, 8],\n        [0, 9, 10, 11, 12],\n        [0, 13, 14, 15, 16],\n        [0, 17, 18, 19, 20],\n\n        \n        [38, 36, 35, 34, 30, 31, 32, 33, 37],\n        [40, 39],\n        [52, 46, 50, 48, 46, 44, 42, 41, 43, 45, 47, 49, 45, 51],\n        [42, 54, 56, 58, 60, 62, 58],\n        [41, 53, 55, 57, 59, 61, 57],\n        [54, 53],\n\n        \n        [80, 81, 82, 83, 84, ],\n        [80, 85, 86, 87, 88],\n        [80, 89, 90, 91, 92],\n        [80, 93, 94, 95, 96],\n        [80, 97, 98, 99, 100], ]\n\n    parquet_df = map_new_to_old_style(parquet_df)\n    frames = sorted(set(parquet_df.frame))\n    first_frame = min(frames)\n    parquet_df[\"color\"] = parquet_df.type.apply(lambda row: assign_colors(row))\n    parquet_df[\"plot_order\"] = parquet_df.apply(lambda row: assign_order(row), axis=1)\n    first_frame_df = parquet_df[parquet_df.frame == first_frame].copy()\n    first_frame_df = first_frame_df.sort_values([\"plot_order\"]).set_index(\"plot_order\")\n\n    frames_l = []\n    for frame in frames:\n        filtered_df = parquet_df[parquet_df.frame == frame].copy()\n        filtered_df = filtered_df.sort_values([\"plot_order\"]).set_index(\"plot_order\")\n        traces = [\n            go.Scatter(\n                x=filtered_df[\"x\"],\n                y=filtered_df[\"y\"],\n                mode=\"markers\",\n                marker=dict(color=filtered_df.color, size=9),\n            )\n        ]\n\n        for i, seg in enumerate(connections):\n            trace = go.Scatter(\n                x=filtered_df.loc[seg][\"x\"],\n                y=filtered_df.loc[seg][\"y\"],\n                mode=\"lines\",\n            )\n            traces.append(trace)\n        frame_data = go.Frame(data=traces, traces=[i for i in range(17)])\n        frames_l.append(frame_data)\n\n    traces = [\n        go.Scatter(\n            x=first_frame_df[\"x\"],\n            y=first_frame_df[\"y\"],\n            mode=\"markers\",\n            marker=dict(color=first_frame_df.color, size=9),\n        )\n    ]\n    for i, seg in enumerate(connections):\n        trace = go.Scatter(\n            x=first_frame_df.loc[seg][\"x\"],\n            y=first_frame_df.loc[seg][\"y\"],\n            mode=\"lines\",\n            line=dict(color=\"black\", width=2),\n        )\n        traces.append(trace)\n    fig = go.Figure(data=traces, frames=frames_l)\n\n    fig.update_layout(\n        width=500,\n        height=800,\n        scene={\n            \"aspectmode\": \"data\",\n        },\n        updatemenus=[\n            {\n                \"buttons\": [\n                    {\n                        \"args\": [\n                            None,\n                            {\n                                \"frame\": {\"duration\": 100, \"redraw\": True},\n                                \"fromcurrent\": True,\n                                \"transition\": {\"duration\": 0},\n                            },\n                        ],\n                        \"label\": \"&#9654;\",\n                        \"method\": \"animate\",\n                    },\n                    {\n                        \"args\": [\n                            [None],\n                            {\n                                \"frame\": {\"duration\": 0, \"redraw\": False},\n                                \"mode\": \"immediate\",\n                                \"transition\": {\"duration\": 0},\n                            },\n                        ],\n                        \"label\": \"&#9612;&#9612;\",\n                        \"method\": \"animate\",\n                    },\n                ],\n                \"direction\": \"left\",\n                \"pad\": {\"r\": 100, \"t\": 100},\n                \"font\": {\"size\": 20},\n                \"type\": \"buttons\",\n                \"x\": 0.1,\n                \"y\": 0,\n                 }\n        ],\n    )\n    camera = dict(up=dict(x=0, y=-1, z=0), eye=dict(x=0, y=0, z=2.5))\n    fig.update_layout(title_text=title, title_x=0.5)\n    fig.update_layout(scene_camera=camera, showlegend=False)\n    fig.update_layout(\n        xaxis=dict(visible=False),\n        yaxis=dict(visible=False),\n    )\n    fig.update_yaxes(autorange=\"reversed\")\n\n    fig.show()\n\n\ndef get_phrase(df, file_id, sequence_id):\n    return df[\n        np.logical_and(df.file_id == file_id, df.sequence_id == sequence_id)\n    ].phrase.iloc[0]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file_id = 474255203\nsequence_id = 53122870\n\nsurprise = f\"/kaggle/input/asl-fingerspelling/train_landmarks/{file_id}.parquet\"\nsurprised = pd.read_parquet(surprise)\n\nsequence = surprised[surprised.index == sequence_id]\nsequence","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import plotly.graph_objects as go\nimport pandas as pd\nget_phrase(train, file_id, sequence_id)\nvisualise2d_landmarks(sequence, \"Surprised\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nframe_number = 578\nlandmark_type = 'face'  # or 'right_hand' or any other valid type\n\n# Filter the DataFrame based on the frame number and landmark type\nfiltered_landmarks = example_landmark[example_landmark['frame'] == frame_number]\n\n# Select the columns for the specific landmark type\nlandmark_columns = [column for column in filtered_landmarks.columns if landmark_type in column]\n\n# Scatter plot the 'x' and 'y' coordinates\nplt.scatter(filtered_landmarks[landmark_columns[::2]], filtered_landmarks[landmark_columns[1::2]])\nplt.xlabel('x')\nplt.ylabel('y')\nplt.title(f'{landmark_type.capitalize()} Landmarks - Frame {frame_number}')\nplt.show()\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# TRY TO USE MEDIAPIPE TO PLOT\n- Pull some example images\n- Run mediapipe holistic to see how it produces the results\n- plot them on the image","metadata":{}},{"cell_type":"code","source":"!wget https://i.ytimg.com/vi/mi9f9zOaqM8/hqdefault.jpg --quiet\n!wget https://purepng.com/public/uploads/large/purepng.com-standing-womenwomenpeoplepersonsfemale-1121525078284xmm0l.png --quiet \n!pip install mediapipe --quiet","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import cv2\nimport mediapipe as mp\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nmp_drawing = mp.solutions.drawing_utils\nmp_drawing_styles = mp.solutions.drawing_styles\nmp_holistic = mp.solutions.holistic\n\n# For static images:\nIMAGE_FILES = [\"hqdefault.jpg\",\n               \"purepng.com-standing-womenwomenpeoplepersonsfemale-1121525078284xmm0l.png\"]\nBG_COLOR = (192, 192, 192)  # gray\n\nwith mp_holistic.Holistic(\n    static_image_mode=True,\n    model_complexity=2,\n    enable_segmentation=True,\n    refine_face_landmarks=True\n) as holistic:\n    for idx, file in enumerate(IMAGE_FILES):\n        image = cv2.imread(file)\n        if image is None:\n            print(f\"Failed to read image file: {file}\")\n            continue\n\n        image_height, image_width, _ = image.shape\n        # Convert the BGR image to RGB before processing.\n        results = holistic.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))\n\n        if results.pose_landmarks:\n            print(\n                f'Nose coordinates: ('\n                f'{results.pose_landmarks.landmark[mp_holistic.PoseLandmark.NOSE].x * image_width}, '\n                f'{results.pose_landmarks.landmark[mp_holistic.PoseLandmark.NOSE].y * image_height})'\n            )\n\n        annotated_image = image.copy()\n        condition = np.stack((results.segmentation_mask,) * 3, axis=-1) > 0.1\n        bg_image = np.zeros(image.shape, dtype=np.uint8)\n        bg_image[:] = BG_COLOR\n        annotated_image = np.where(condition, annotated_image, bg_image)\n        mp_drawing.draw_landmarks(\n            annotated_image,\n            results.face_landmarks,\n            mp_holistic.FACEMESH_TESSELATION,\n            landmark_drawing_spec=None,\n            connection_drawing_spec=mp_drawing_styles.get_default_face_mesh_tesselation_style()\n        )\n        mp_drawing.draw_landmarks(\n            annotated_image,\n            results.pose_landmarks,\n            mp_holistic.POSE_CONNECTIONS,\n            landmark_drawing_spec=mp_drawing_styles.get_default_pose_landmarks_style()\n        )\n        cv2.imwrite(f'/tmp/annotated_image{idx}.png', annotated_image)\n        # Plot pose world landmarks.\n        mp_drawing.plot_landmarks(\n            results.pose_world_landmarks, mp_holistic.POSE_CONNECTIONS\n        )\n\n        # Display annotated image using matplotlib\n        plt.imshow(plt.imread(f\"/tmp/annotated_image{idx}.png\"))\n        plt.show()\n\n# For webcam input:\ncap = cv2.VideoCapture(0)\nwith mp_holistic.Holistic(\n    min_detection_confidence=0.5,\n    min_tracking_confidence=0.5\n) as holistic:\n    while cap.isOpened():\n        success, image = cap.read()\n        if not success:\n            print(\"Ignoring empty camera frame.\")\n            # If loading a video, use 'break' instead of 'continue'.\n            continue\n\n        image.flags.writeable = False\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        results = holistic.process(image)\n\n        # Draw landmark annotation on the image.\n        image.flags.writeable = True\n        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)\n        mp_drawing.draw_landmarks(\n            image,\n            results.face_landmarks,\n            mp_holistic.FACEMESH_CONTOURS,\n            landmark_drawing_spec=None,\n            connection_drawing_spec=mp_drawing_styles.get_default_face_mesh_contours_style()\n        )\n        mp_drawing.draw_landmarks(\n            image,\n            results.pose_landmarks,\n            mp_holistic.POSE_CONNECTIONS,\n            landmark_drawing_spec=mp_drawing_styles.get_default_pose_landmarks_style()\n        )\n        # Flip the image horizontally for a selfie-view display.\n        cv2.imshow('MediaPipe Holistic', cv2.flip(image, 1))\n        if cv2.waitKey(5) & 0xFF == 27:\n            cap.release()\n            break\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Try to use the same format for plotting of parquet data","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\n\nbackground_image = np.zeros([720, 720, 3])\nmp_drawing.draw_landmarks(\n    background_image,\n    results.face_landmarks,\n    mp_holistic.FACEMESH_TESSELATION,\n    landmark_drawing_spec=None,\n    connection_drawing_spec=mp_drawing_styles.get_default_face_mesh_tesselation_style(),\n)\nmp_drawing.draw_landmarks(\n    background_image,\n    results.pose_landmarks,\n    mp_holistic.POSE_CONNECTIONS,\n    landmark_drawing_spec=mp_drawing_styles.get_default_pose_landmarks_style()\n)\nplt.imshow(background_image)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"type(results.face_landmarks)\nfrom mediapipe.framework.formats import landmark_pb2","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\n\nface_columns = [col for col in example_frame.columns if 'face' in col]\nfiltered_frame = example_frame[\n    (example_frame[face_columns] == 'face').all(axis=1) & ~example_frame[face_columns].isna().any(axis=1)\n]\nprint(filtered_frame)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import mediapipe as mp\nmp_drawing = mp.solutions.drawing_utils\nmp_drawing.draw_landmarks(\n    background_image,\n    results.face_landmarks,\n    mp_holistic.FACEMESH_TESSELATION,\n    landmark_drawing_spec=None,\n    connection_drawing_spec=mp_drawing_styles.get_default_face_mesh_tesselation_style(),\n)\nplt.imshow(background_image)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import plotly.graph_objects as go\nimport pandas as pd\n\n# Assuming your dataset is stored in a pandas DataFrame called 'df'\ndf = pd.DataFrame({\n    'frame': [86, 86, 86, 86, 86],\n    'x_face': [0.574436, 0.620399, 0.550710, 0.615361, 0.473677],\n    'y_face': [0.560474, 0.604428, 0.539382, 0.603240, 0.468712],\n    'z_face': [0.566295, 0.609184, 0.545007, 0.609855, 0.470851],\n    'x_right_hand': [0.482442, 0.475004, 0.463145, 0.520459, 0.327291],\n    'y_right_hand': [0.563047, 0.598960, 0.537619, 0.608835, 0.478398],\n    'z_right_hand': [0.543066, -0.058136, 0.550710, 0.613422, -0.171806],\n    # Add more columns as necessary\n})\n\nfig = go.Figure(data=[go.Scatter3d(\n    x=df['x_face'],\n    y=df['y_face'],\n    z=df['z_face'],\n    mode='markers',\n    marker=dict(\n        size=5,\n        color=df['frame'],  # Color based on the 'frame' column\n        colorscale='Viridis',\n        opacity=0.8\n    )\n)])\n\n# Add more columns to the plot if needed\nfig.add_trace(go.Scatter3d(\n    x=df['x_right_hand'],\n    y=df['y_right_hand'],\n    z=df['z_right_hand'],\n    mode='markers',\n    marker=dict(\n        size=5,\n        color=df['frame'],  # Color based on the 'frame' column\n        colorscale='Viridis',\n        opacity=0.8\n    )\n))\n\nfig.show()\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# TODO\nFigure out how to transform the parquet file data into mediapipe NormalizedLandmarkList","metadata":{}},{"cell_type":"markdown","source":"**EVALUATION**","metadata":{}},{"cell_type":"code","source":"def load_relevant_data_subset(pq_path):\n    return pd.read_parquet(pq_path, columns=selected_columns)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Inference is performed (roughly) as follows, ignoring details like how we manage multiple videos:","metadata":{}},{"cell_type":"code","source":"#import tflite_runtime.interpreter as tflite\n#def run_model(model_path):\n    #interpreter = tflite.Interpreter(model_path)\n    #REQUIRED_SIGNATURE = \"serving_default\"\n    #REQUIRED_OUTPUT = \"outputs\"\n    #with open (\"/kaggle/input/fingerspelling-character-map/character_to_prediction_index.json\", \"r\") as f:\n    #character_map = json.load(f)\n    #rev_character_map = {j:i for i,j in character_map.items()}\n    \n    #found_signatures = list(interpreter.get_signature_list().keys())\n    #if REQUIRED_SIGNATURE not in found_signatures:\n        #raise KernelEvalException('Required input signature not found.')\n    #prediction_fn = interpreter.get_signature_runner(\"serving_default\")\n    #output = prediction_fn(inputs=frames)\n    #prediction_str = \"\".join([rev_character_map.get(s, \"\") for s in np.argmax(output[REQUIRED_OUTPUT], axis=1)])","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}