{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":81933,"databundleVersionId":9643020,"sourceType":"competition"}],"dockerImageVersionId":30786,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# 🕸️Generative Adversarial Networks - 🧑💻Problametic Internet Usage
\n\n\n\n# 🎒Import Libraries","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport polars as pl\nimport pandas as pd\nfrom sklearn.base import clone\nfrom copy import deepcopy\nimport optuna\nfrom scipy.optimize import minimize\nimport os\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nimport re\nfrom colorama import Fore, Style\n\nfrom tqdm import tqdm\nfrom IPython.display import clear_output\nfrom concurrent.futures import ThreadPoolExecutor\n\nimport warnings\nwarnings.filterwarnings('ignore')\npd.options.display.max_columns = None\n\nimport lightgbm as lgb\n# from catboost import CatBoostRegressor, CatBoostClassifier\nimport xgboost as xgb\nfrom sklearn.ensemble import VotingRegressor\nfrom sklearn.model_selection import *\nfrom sklearn.metrics import *\n\nSEED = 42\nn_splits = 5\n\n#For GANs\nfrom keras.models import Sequential\nfrom keras.layers import Dense, LeakyReLU, Dropout\nfrom keras.optimizers import Adam\nfrom sklearn.preprocessing import MinMaxScaler\nfrom sklearn.model_selection import train_test_split\nimport random\nimport tensorflow as tf","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-10-19T17:53:02.977445Z","iopub.execute_input":"2024-10-19T17:53:02.977876Z","iopub.status.idle":"2024-10-19T17:53:02.987618Z","shell.execute_reply.started":"2024-10-19T17:53:02.977838Z","shell.execute_reply":"2024-10-19T17:53:02.986630Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ✨Preprocessing","metadata":{}},{"cell_type":"code","source":"def process_file(filename, dirname):\n df = pd.read_parquet(os.path.join(dirname, filename, 'part-0.parquet'))\n df.drop('step', axis=1, inplace=True)\n return df.describe().values.reshape(-1), filename.split('=')[1]\n\ndef load_time_series(dirname) -> pd.DataFrame:\n ids = os.listdir(dirname)\n \n with ThreadPoolExecutor() as executor:\n results = list(tqdm(executor.map(lambda fname: process_file(fname, dirname), ids), total=len(ids)))\n \n stats, indexes = zip(*results)\n \n df = pd.DataFrame(stats, columns=[f\"Stat_{i}\" for i in range(len(stats[0]))])\n df['id'] = indexes\n \n return df\n\ntrain = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/train.csv')\ntest = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/test.csv')\nsample = pd.read_csv('/kaggle/input/child-mind-institute-problematic-internet-use/sample_submission.csv')\n\ntrain_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_train.parquet\")\ntest_ts = load_time_series(\"/kaggle/input/child-mind-institute-problematic-internet-use/series_test.parquet\")\ntime_series_cols = test_ts.columns.tolist()\ntime_series_cols.remove(\"id\")\n\ntrain = pd.merge(train, train_ts, how=\"left\", on='id')\ntest = pd.merge(test, test_ts, how=\"left\", on='id')\n\ntrain = train.drop('id', axis=1)\ntest = test.drop('id', axis=1)\n\nfeaturesCols = ['Basic_Demos-Enroll_Season', 'Basic_Demos-Age', 'Basic_Demos-Sex',\n 'CGAS-Season', 'CGAS-CGAS_Score', 'Physical-Season', 'Physical-BMI',\n 'Physical-Height', 'Physical-Weight', 'Physical-Waist_Circumference',\n 'Physical-Diastolic_BP', 'Physical-HeartRate', 'Physical-Systolic_BP',\n 'Fitness_Endurance-Season', 'Fitness_Endurance-Max_Stage',\n 'Fitness_Endurance-Time_Mins', 'Fitness_Endurance-Time_Sec',\n 'FGC-Season', 'FGC-FGC_CU', 'FGC-FGC_CU_Zone', 'FGC-FGC_GSND',\n 'FGC-FGC_GSND_Zone', 'FGC-FGC_GSD', 'FGC-FGC_GSD_Zone', 'FGC-FGC_PU',\n 'FGC-FGC_PU_Zone', 'FGC-FGC_SRL', 'FGC-FGC_SRL_Zone', 'FGC-FGC_SRR',\n 'FGC-FGC_SRR_Zone', 'FGC-FGC_TL', 'FGC-FGC_TL_Zone', 'BIA-Season',\n 'BIA-BIA_Activity_Level_num', 'BIA-BIA_BMC', 'BIA-BIA_BMI',\n 'BIA-BIA_BMR', 'BIA-BIA_DEE', 'BIA-BIA_ECW', 'BIA-BIA_FFM',\n 'BIA-BIA_FFMI', 'BIA-BIA_FMI', 'BIA-BIA_Fat', 'BIA-BIA_Frame_num',\n 'BIA-BIA_ICW', 'BIA-BIA_LDM', 'BIA-BIA_LST', 'BIA-BIA_SMM',\n 'BIA-BIA_TBW', 'PAQ_A-Season', 'PAQ_A-PAQ_A_Total', 'PAQ_C-Season',\n 'PAQ_C-PAQ_C_Total', 'SDS-Season', 'SDS-SDS_Total_Raw',\n 'SDS-SDS_Total_T', 'PreInt_EduHx-Season',\n 'PreInt_EduHx-computerinternet_hoursday', 'sii']\n\nfeaturesCols += time_series_cols\n\ntrain = train[featuresCols]\ntrain = train.dropna(subset='sii')\n\ncat_c = ['Basic_Demos-Enroll_Season', 'CGAS-Season', 'Physical-Season', 'Fitness_Endurance-Season', \n 'FGC-Season', 'BIA-Season', 'PAQ_A-Season', 'PAQ_C-Season', 'SDS-Season', 'PreInt_EduHx-Season']\n\ndef update(df):\n for c in cat_c: \n df[c] = df[c].fillna('Missing')\n df[c] = df[c].astype('category')\n return df\n \ntrain = update(train)\ntest = update(test)\n\ndef create_mapping(column, dataset):\n unique_values = dataset[column].unique()\n return {value: idx for idx, value in enumerate(unique_values)}\n\nfor col in cat_c:\n mapping_train = create_mapping(col, train)\n mapping_test = create_mapping(col, test)\n \n train[col] = train[col].replace(mapping_train).astype(int)\n test[col] = test[col].replace(mapping_test).astype(int)\n\nprint(f'Train Shape : {train.shape} || Test Shape : {test.shape}')","metadata":{"execution":{"iopub.status.busy":"2024-10-19T17:53:03.013125Z","iopub.execute_input":"2024-10-19T17:53:03.013858Z","iopub.status.idle":"2024-10-19T17:54:28.616720Z","shell.execute_reply.started":"2024-10-19T17:53:03.013824Z","shell.execute_reply":"2024-10-19T17:54:28.615637Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🕸️Generative Adversarial Networks","metadata":{}},{"cell_type":"code","source":"import time\nstart_time = time.time()\n\n# Set random seeds for reproducibility\nGAN_SEED=42\nrandom.seed(GAN_SEED)\nnp.random.seed(GAN_SEED)\ntf.random.set_seed(GAN_SEED)\n\n# Load and preprocess data\ntrain_data = train\nX = train_data.drop(columns=['sii'])\ny = train_data['sii']\nscaler_X = MinMaxScaler()\nscaler_y = MinMaxScaler()\nX_scaled = scaler_X.fit_transform(X)\ny_scaled = scaler_y.fit_transform(y.values.reshape(-1, 1))\ntrain_data = train_data.values #convert pd dataframe to np array\n\n# Generator model\ndef build_generator(input_dim, output_dim):\n model = Sequential()\n model.add(Dense(128, input_dim=input_dim))\n model.add(LeakyReLU(alpha=0.2))\n model.add(Dense(256))\n model.add(LeakyReLU(alpha=0.2))\n model.add(Dense(512))\n model.add(LeakyReLU(alpha=0.2))\n model.add(Dense(output_dim, activation='linear'))\n return model\n\n# Discriminator model\ndef build_discriminator(input_dim):\n model = Sequential()\n model.add(Dense(512, input_dim=input_dim))\n model.add(LeakyReLU(alpha=0.2))\n model.add(Dropout(0.3))\n model.add(Dense(256))\n model.add(LeakyReLU(alpha=0.2))\n model.add(Dropout(0.3))\n model.add(Dense(1, activation='sigmoid'))\n return model\n\n# GAN model\ndef build_gan(generator, discriminator):\n model = Sequential()\n model.add(generator)\n discriminator.trainable = False\n model.add(discriminator)\n return model\n\n# Compile models\ninput_dim = train_data.shape[1]\noutput_dim = train_data.shape[1]\ndiscriminator = build_discriminator(output_dim)\ndiscriminator.compile(optimizer=Adam(learning_rate=0.0002, beta_1=0.5), loss='binary_crossentropy', metrics=['accuracy'])\ngenerator = build_generator(input_dim=input_dim, output_dim=output_dim)\ngan = build_gan(generator, discriminator)\ngan.compile(optimizer=Adam(learning_rate=0.0002, beta_1=0.5), loss='binary_crossentropy')\n\n# Training function\ndef train_gan(generator, discriminator, gan, epochs, batch_size, noise_dim, patience=500):\n real_label = np.ones((batch_size, 1))\n fake_label = np.zeros((batch_size, 1))\n best_g_loss = np.inf\n patience_counter = 0\n \n for epoch in range(epochs):\n # Train discriminator on real data\n idx = np.random.randint(0, train_data.shape[0], batch_size)\n real_data = train_data[idx]\n d_loss_real = discriminator.train_on_batch(real_data, real_label)\n \n # Train discriminator on fake data\n noise = np.random.normal(0, 1, (batch_size, noise_dim))\n fake_data = generator.predict(noise)\n d_loss_fake = discriminator.train_on_batch(fake_data, fake_label)\n d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)\n \n # Train generator via GAN\n noise = np.random.normal(0, 1, (batch_size, noise_dim))\n g_loss = gan.train_on_batch(noise, real_label)\n\n # Extract the generator loss value (if it's a list, take the first element)\n g_loss_value = g_loss[0] if isinstance(g_loss, list) else g_loss\n \n # Check for early stopping\n if g_loss_value < best_g_loss:\n best_g_loss = g_loss_value\n patience_counter = 0\n else:\n patience_counter += 1\n\n if patience_counter > patience:\n print(f\"Early stopping at epoch {epoch} due to no improvement in generator loss\")\n break\n \n if epoch % 100 == 0:\n print(f\"Epoch {epoch}, Discriminator Loss: {d_loss[0]}, Generator Loss: {g_loss_value}\")\n\n# Train GAN\nepochs = 10000\nbatch_size = 64\nnoise_dim = input_dim\ntrain_gan(generator, discriminator, gan, epochs, batch_size, noise_dim)\n\n# Generate synthetic data\nnoise = np.random.normal(0, 1, (10000, noise_dim))\nsynthetic_data = generator.predict(noise)\nsynthetic_X = synthetic_data[:, :-1]\nsynthetic_y = synthetic_data[:, -1]\nsynthetic_X = scaler_X.inverse_transform(synthetic_X)\nsynthetic_y = scaler_y.inverse_transform(synthetic_y.reshape(-1, 1))\n\n# Clip and round the generated sii values to ensure they are in the set {0, 1, 2, 3}\nsynthetic_y = np.clip(np.round(synthetic_y), 0, 3)\n\n# Combine synthetic features and target into a single DataFrame\nsynthetic_data = np.hstack((synthetic_X, synthetic_y))\n\ncolumns_names = list(X.columns) + ['sii'] # Assuming 'sii' is the target column\nsynthetic_df = pd.DataFrame(synthetic_data, columns=columns_names)\n\n# Save the synthetic data to a CSV file\n\n# Combine train scaled features and target into a single DataFrame\ny_scaled = np.clip(np.round(y_scaled), 0, 3)\ntrain_org_data = pd.DataFrame(np.hstack((X_scaled, y_scaled)),columns=columns_names)\n\n# Concatenate train_data and syn_data along the rows (axis=0)\ntrain = pd.concat([train_org_data, synthetic_df], axis=0, ignore_index=True)\n# combined_data.to_csv('cmi_train_and_synthetic_data.csv', index=False)\n\nprint(\"Synthetic data saved to synthetic_data.csv\")\nprint(train['sii'].value_counts())\nprint(train.shape)\n\nend_time = time.time()\nelapsed_time = end_time - start_time\nprint(\"Time elapsed:\", elapsed_time, \"seconds\")","metadata":{"execution":{"iopub.status.busy":"2024-10-19T17:54:28.618540Z","iopub.execute_input":"2024-10-19T17:54:28.618878Z","iopub.status.idle":"2024-10-19T17:58:29.710852Z","shell.execute_reply.started":"2024-10-19T17:54:28.618844Z","shell.execute_reply":"2024-10-19T17:58:29.709839Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🗃️Modeling","metadata":{}},{"cell_type":"code","source":"def quadratic_weighted_kappa(y_true, y_pred):\n return cohen_kappa_score(y_true, y_pred, weights='quadratic')\n\ndef threshold_Rounder(oof_non_rounded, thresholds):\n return np.where(oof_non_rounded < thresholds[0], 0,\n np.where(oof_non_rounded < thresholds[1], 1,\n np.where(oof_non_rounded < thresholds[2], 2, 3)))\n\ndef evaluate_predictions(thresholds, y_true, oof_non_rounded):\n rounded_p = threshold_Rounder(oof_non_rounded, thresholds)\n return -quadratic_weighted_kappa(y_true, rounded_p)\n\ndef TrainML(model_class, test_data):\n \n X = train.drop(['sii'], axis=1)\n y = train['sii']\n\n SKF = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=SEED)\n \n train_S = []\n test_S = []\n \n oof_non_rounded = np.zeros(len(y), dtype=float) \n oof_rounded = np.zeros(len(y), dtype=int) \n test_preds = np.zeros((len(test_data), n_splits))\n\n for fold, (train_idx, test_idx) in enumerate(tqdm(SKF.split(X, y), desc=\"Training Folds\", total=n_splits)):\n X_train, X_val = X.iloc[train_idx], X.iloc[test_idx]\n y_train, y_val = y.iloc[train_idx], y.iloc[test_idx]\n\n model = clone(model_class)\n model.fit(X_train, y_train)\n\n y_train_pred = model.predict(X_train)\n y_val_pred = model.predict(X_val)\n\n oof_non_rounded[test_idx] = y_val_pred\n y_val_pred_rounded = y_val_pred.round(0).astype(int)\n oof_rounded[test_idx] = y_val_pred_rounded\n\n train_kappa = quadratic_weighted_kappa(y_train, y_train_pred.round(0).astype(int))\n val_kappa = quadratic_weighted_kappa(y_val, y_val_pred_rounded)\n\n train_S.append(train_kappa)\n test_S.append(val_kappa)\n \n test_preds[:, fold] = model.predict(test_data)\n \n print(f\"Fold {fold+1} - Train QWK: {train_kappa:.4f}, Validation QWK: {val_kappa:.4f}\")\n# clear_output(wait=True)\n\n print(f\"Mean Train QWK --> {np.mean(train_S):.4f}\")\n print(f\"Mean Validation QWK ---> {np.mean(test_S):.4f}\")\n\n KappaOPtimizer = minimize(evaluate_predictions,\n x0=[0.5, 1.5, 2.5], args=(y, oof_non_rounded), \n method='Nelder-Mead') # Nelder-Mead | # Powell\n assert KappaOPtimizer.success, \"Optimization did not converge.\"\n \n oof_tuned = threshold_Rounder(oof_non_rounded, KappaOPtimizer.x)\n tKappa = quadratic_weighted_kappa(y, oof_tuned)\n\n print(f\"----> || Optimized QWK SCORE :: {Fore.CYAN}{Style.BRIGHT} {tKappa:.3f}{Style.RESET_ALL}\")\n\n tpm = test_preds.mean(axis=1)\n tpTuned = threshold_Rounder(tpm, KappaOPtimizer.x)\n \n submission = pd.DataFrame({\n 'id': sample['id'],\n 'sii': tpTuned\n })\n\n return submission,model","metadata":{"execution":{"iopub.status.busy":"2024-10-19T17:58:29.712330Z","iopub.execute_input":"2024-10-19T17:58:29.712736Z","iopub.status.idle":"2024-10-19T17:58:29.729708Z","shell.execute_reply.started":"2024-10-19T17:58:29.712698Z","shell.execute_reply":"2024-10-19T17:58:29.728738Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🛡️LGBMRegressor","metadata":{}},{"cell_type":"code","source":"Params7 = {\n 'learning_rate': 0.03884249148676395, \n 'max_depth': 12, \n 'num_leaves': 413, \n 'min_data_in_leaf': 14,\n 'feature_fraction': 0.7987976913702801, \n 'bagging_fraction': 0.7602261703576205, \n 'bagging_freq': 2, \n 'lambda_l1': 4.735462555910575, \n 'lambda_l2': 4.735028557007343e-06\n } \n\nLight = lgb.LGBMRegressor(**Params7,random_state=SEED, verbose=-1,n_estimators=250, device='gpu')\nSubmission,model = TrainML(Light,test)","metadata":{"execution":{"iopub.status.busy":"2024-10-19T17:58:29.732080Z","iopub.execute_input":"2024-10-19T17:58:29.732429Z","iopub.status.idle":"2024-10-19T17:58:59.260656Z","shell.execute_reply.started":"2024-10-19T17:58:29.732384Z","shell.execute_reply":"2024-10-19T17:58:59.259510Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 📁Submission","metadata":{}},{"cell_type":"code","source":"Submission.to_csv('submission.csv', index=False)\nprint(Submission['sii'].value_counts())","metadata":{"execution":{"iopub.status.busy":"2024-10-19T17:58:59.262676Z","iopub.execute_input":"2024-10-19T17:58:59.263439Z","iopub.status.idle":"2024-10-19T17:58:59.271258Z","shell.execute_reply.started":"2024-10-19T17:58:59.263380Z","shell.execute_reply":"2024-10-19T17:58:59.270018Z"},"trusted":true},"execution_count":null,"outputs":[]}]}