{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":52950,"databundleVersionId":5973250,"sourceType":"competition"}],"dockerImageVersionId":31089,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## Dataset Description\n\n## Files\n\n### [train/supplemental_metadata].csv\n- path - The path to the landmark file.\n- file_id - A unique identifier for the data file.\n- participant_id - A unique identifier for the data contributor.\n- sequence_id - A unique identifier for the landmark sequence. Each data file may contain many sequences.\n- phrase - The labels for the landmark sequence.\n\ncompetiton link : https://www.kaggle.com/competitions/asl-fingerspelling/","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport matplotlib.pyplot as plt","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-08-01T15:12:15.455552Z","iopub.execute_input":"2025-08-01T15:12:15.456363Z","iopub.status.idle":"2025-08-01T15:12:15.460546Z","shell.execute_reply.started":"2025-08-01T15:12:15.456326Z","shell.execute_reply":"2025-08-01T15:12:15.459448Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df = pd.read_csv('/kaggle/input/asl-fingerspelling/train.csv')\ntrain_df_sorted = train_df.sort_values(by='phrase',key=lambda x: x.str.len())\ntrain_df_sorted","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T15:12:15.485351Z","iopub.execute_input":"2025-08-01T15:12:15.486524Z","iopub.status.idle":"2025-08-01T15:12:15.658544Z","shell.execute_reply.started":"2025-08-01T15:12:15.486492Z","shell.execute_reply":"2025-08-01T15:12:15.657543Z"},"scrolled":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### The chosen word is 'surprise'","metadata":{}},{"cell_type":"code","source":"phrase = 'surprise az'\ntrain_df_sorted['phrase'] = train_df_sorted['phrase'].str.strip()\ntrain_df_sorted = train_df_sorted[train_df_sorted['phrase'] == phrase]\ntrain_df_sorted","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T15:12:15.659891Z","iopub.execute_input":"2025-08-01T15:12:15.660214Z","iopub.status.idle":"2025-08-01T15:12:15.710213Z","shell.execute_reply.started":"2025-08-01T15:12:15.660192Z","shell.execute_reply":"2025-08-01T15:12:15.709172Z"},"scrolled":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"participant_136_df = pd.read_parquet('/kaggle/input/asl-fingerspelling/train_landmarks/1969985709.parquet')\nparticipant_136_df_seq = participant_136_df[participant_136_df.index == 1595884623]\nparticipant_136_df_seq.isna().sum()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T15:12:15.711333Z","iopub.execute_input":"2025-08-01T15:12:15.711597Z","iopub.status.idle":"2025-08-01T15:12:19.572334Z","shell.execute_reply.started":"2025-08-01T15:12:15.711575Z","shell.execute_reply":"2025-08-01T15:12:19.571518Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"participant_136_df_seq","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T15:12:19.574423Z","iopub.execute_input":"2025-08-01T15:12:19.574675Z","iopub.status.idle":"2025-08-01T15:12:19.617362Z","shell.execute_reply.started":"2025-08-01T15:12:19.574655Z","shell.execute_reply":"2025-08-01T15:12:19.616382Z"},"scrolled":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"participant_168_df = pd.read_parquet('/kaggle/input/asl-fingerspelling/train_landmarks/1557244878.parquet')\nparticipant_168_df_seq = participant_168_df[participant_168_df.index == 331596218]\nparticipant_168_df_seq.isna().sum()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T15:12:39.717421Z","iopub.execute_input":"2025-08-01T15:12:39.718403Z","iopub.status.idle":"2025-08-01T15:12:43.272549Z","shell.execute_reply.started":"2025-08-01T15:12:39.718366Z","shell.execute_reply":"2025-08-01T15:12:43.271548Z"},"scrolled":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"participant_168_df_seq","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-01T15:12:46.301184Z","iopub.execute_input":"2025-08-01T15:12:46.301485Z","iopub.status.idle":"2025-08-01T15:12:46.327362Z","shell.execute_reply.started":"2025-08-01T15:12:46.301463Z","shell.execute_reply":"2025-08-01T15:12:46.325813Z"}},"outputs":[],"execution_count":null}]}