![\"Heat](\"https://media1.giphy.com/media/Co5TKVg51CmFsxPpNP/giphy.webp\")
Google ASL Fingerspelling
\n✋ EDA and PREPROCESSING ✋
\n\n TABLE OF CONTENTS
\n\n* [1. DATA OVERVIEW](#1)\n \n - [Import Libraries](#1.1)\n \n - [Loading dataset](#1.2)\n \n - [Data Description](#1.3)\n \n* [2. Exploratory Data Analysis](#2)\n \n - [Inspect the PATH column](#2.1)\n\n - [Inspect the PARTICIPANT_ID Column](#2.2)\n \n - [Inspect the SEQUENCE_ID Column](#2.3)\n \n -[Inspect the PHASES Column](#2.4)\n \n -[Inspect the PARQUET Column](#2.5)\n \n* [3. PREPROCESSING DATA](#3)\n\n* [4. Go Further](#4)\n\n - [Calculating Levenshtein Distance](#4.1)\n \n - [Data Preparation and Splitting](#4.2)\n \n - [Model Definition](#4.3)\n \n - [Optimization Setup](#4.4)\n \n - [Training Loop](#4.5)\n \n - [Evaluation](#4.6) \n \n\n#1. DATA OVERVIEW
\n\n\nIn this notebook, we will be exploring and analyzing the Apple stock prices dataset. We will start by importing important libraries, loading the data, and giving a brief description of the dataset.\n\n\n2. EXPLORATORY DATA ANALYSIS
","metadata":{}},{"cell_type":"markdown","source":"\n\n3. PREPROCESSING DATA
\n\nIn this section the datais processed to extract relevant features, and prepared the dataset for further analysis and model training. The processed data can be used for building machine learning models, such as neural networks, to predict the ASL finger spelling from the hand landmarks.","metadata":{}},{"cell_type":"code","source":"sample = pd.read_parquet('/kaggle/input/asl-fingerspelling/train_landmarks/1021040628.parquet')\nLANDMARK_FILES_DIR = \"/kaggle/input/asl-fingerspelling/train_landmarks\"\nTRAIN_FILE = \"/kaggle/input/asl-fingerspelling/train.csv\"\nlabel_map = json.load(open(\"/kaggle/input/asl-fingerspelling/character_to_prediction_index.json\", \"r\"))","metadata":{"execution":{"iopub.status.busy":"2023-06-20T17:40:07.558411Z","iopub.execute_input":"2023-06-20T17:40:07.559244Z","iopub.status.idle":"2023-06-20T17:40:12.2954Z","shell.execute_reply.started":"2023-06-20T17:40:07.559211Z","shell.execute_reply":"2023-06-20T17:40:12.294482Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(label_map)","metadata":{"execution":{"iopub.status.busy":"2023-06-20T17:40:14.825384Z","iopub.execute_input":"2023-06-20T17:40:14.825982Z","iopub.status.idle":"2023-06-20T17:40:14.832456Z","shell.execute_reply.started":"2023-06-20T17:40:14.825943Z","shell.execute_reply":"2023-06-20T17:40:14.83158Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"So there are 59 characters in total in the vocabulary. :\n\n alphabets a-z : total 26 characters\n digits : 0-9 , 10 in total\n The rest are special characters. Let's look at them","metadata":{}},{"cell_type":"code","source":"# Memory saving function credit to https://www.kaggle.com/gemartin/load-data-reduce-memory-usage\ndef reduce_mem_usage(df):\n \"\"\" iterate through all the columns of a dataframe and modify the data type\n to reduce memory usage. \n \"\"\"\n #start_mem = df.memory_usage().sum() / 1024**2\n #print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))\n\n for col in df.columns:\n col_type = df[col].dtype\n\n if col_type != object:\n c_min = df[col].min()\n c_max = df[col].max()\n if str(col_type)[:3] == 'int':\n if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n df[col] = df[col].astype(np.int8)\n elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n df[col] = df[col].astype(np.int16)\n elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n df[col] = df[col].astype(np.int32)\n elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n df[col] = df[col].astype(np.int64) \n else:\n if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n df[col] = df[col].astype(np.float16)\n elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n df[col] = df[col].astype(np.float32)\n else:\n df[col] = df[col].astype(np.float64)\n\n return df","metadata":{"execution":{"iopub.status.busy":"2023-06-20T17:40:17.260511Z","iopub.execute_input":"2023-06-20T17:40:17.260926Z","iopub.status.idle":"2023-06-20T17:40:17.273145Z","shell.execute_reply.started":"2023-06-20T17:40:17.260894Z","shell.execute_reply":"2023-06-20T17:40:17.272146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import multiprocessing as mp\nimport pandas as pd\nimport torch\nimport numpy as np\n\n# Function to process a single parquet file\ndef process_parquet(row):\n path = os.path.join(\"/kaggle/input/asl-fingerspelling\", row[1].path)\n data_columns = COLUMNS\n landmark_df = pd.read_parquet(path, columns=data_columns)\n\n # Group the landmarks by sequence_id\n grouped_landmarks = landmark_df.groupby('sequence_id')\n\n # Initialize empty lists to store features and labels\n features = []\n labels = []\n\n # Iterate over each sequence_id\n for sequence_id, group in grouped_landmarks:\n # Get the label for the sequence\n phrase = df.loc[df['sequence_id'] == sequence_id, 'phrase'].iloc[0]\n\n # Map each letter in the phrase using label_map\n mapped_phrase = [letter for letter in phrase]\n \n # Create a new Series with sequence and mapped_phrase\n result_series = pd.DataFrame({'sequence_id': sequence_id, 'mapped_phrase': mapped_phrase}) \n result_series['label'] = result_series['mapped_phrase'].map(label_map).astype(np.int8) \n\n # Convert the label Series to a list\n #label_list = result_series['label'].tolist()\n\n # Initialize an empty feature vector for the sequence\n sequence_features = []\n \n # Iterate over each landmark index\n for landmark_index in range(20):\n # Generate feature names for x, y, z coordinates\n x_feature = f'x_right_hand_{landmark_index}'\n y_feature = f'y_right_hand_{landmark_index}'\n\n # Get the x, y, z coordinates for the landmark\n x = group[x_feature].values.astype(np.float16)\n y = group[y_feature].values.astype(np.float16)\n\n # Replace NaN values with 0\n x[np.isnan(x)] = 0.0\n y[np.isnan(y)] = 0.0\n \n # Perform feature transformations or calculations\n x = torch.tensor(x).contiguous().view(-1, x.shape[0])\n y = torch.tensor(y).contiguous().view(-1, y.shape[0])\n \n x_mean = torch.mean(x, 0) \n y_mean = torch.mean(y, 0) \n\n x_std = torch.std(x, 1) \n y_std = torch.std(y, 1) \n\n # Add the calculated features to the sequence feature vector\n sequence_features = torch.cat([x_mean, y_mean,x_std,y_std], axis=0)\n #sequence_features = torch.where(torch.isnan(sequence_features), torch.tensor(0.0, dtype=torch.float32), sequence_features)\n\n diff = 3258 - sequence_features.shape[0]\n if diff > 0:\n padding = torch.zeros(diff)\n sequence_features = torch.cat((sequence_features, padding))\n \n features = sequence_features[:3258].cpu().numpy()\n \n \n return features, result_series['label']\n\nif __name__ == '__main__':\n df = pd.read_csv(TRAIN_FILE)\n df = reduce_mem_usage(df) \n df2 = df.head(30)\n\n max_label_length = 30\n all_features = np.zeros((df.shape[0], 3258))\n labels = np.zeros((df.shape[0], max_label_length))\n #all_features = []\n #labels = []\n\n # Process parquet files in parallel\n with mp.Pool() as pool:\n results = pool.imap(process_parquet, df.iterrows(), chunksize=250)\n for i, (x, y) in tqdm(enumerate(results), total=df.shape[0]):\n all_features[i, :] = x\n labels[i, :len(y)] = y.values.reshape(1, -1)\n\n # Print the shapes of the tensors\n np.save(\"feature_data.npy\", all_features)\n np.save(\"feature_labels.npy\", labels)\n\n print(\"Features tensor shape:\", all_features.shape)\n print(\"Labels tensor shape:\", labels.shape)\n","metadata":{"execution":{"iopub.status.busy":"2023-06-20T17:40:28.96055Z","iopub.execute_input":"2023-06-20T17:40:28.960937Z","iopub.status.idle":"2023-06-20T21:07:14.096742Z","shell.execute_reply.started":"2023-06-20T17:40:28.960905Z","shell.execute_reply":"2023-06-20T21:07:14.09567Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The process_parquet function processes a single parquet file. It reads the file, groups the landmarks by sequence_id, retrieves the corresponding label for each sequence, maps the label using label_map, performs feature transformations on the landmarks, and constructs a feature vector for the sequence. The function returns the features and labels for each sequence.\n","metadata":{}},{"cell_type":"markdown","source":"\n\n#4. GO FURTHER
\n\n[ASLFR training & Evaluation Levenshtein dist.](https://www.kaggle.com/code/hebasaleh00/aslfr-training-and-evaluation-with-levenshtein-dis)\n\nThis notebook is a continuation for the Google ASL Finger Recognition competition. In the this notebook, I processed the data and extracted features for the task. In the next notebook, I will train and evaluate a model using the extracted features. Additionally, I will use the Levenshtein distance as a metric to measure the similarity between predicted labels and ground truth labels.\n\n ** If you liked this Notebook, please do forget to upvote, and GooD LucK.**\n\n","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}