Datasets
Models
Downloads: 1
Diff of
/03-Experiments/05-LightBGM_With_FE.ipynb
[000000]
..
[b4c0b6]
Switch to side-by-side view
--- a +++ b/03-Experiments/05-LightBGM_With_FE.ipynb @@ -0,0 +1,866 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Gloabl Experiment Setup" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "2024/04/25 15:58:03 INFO mlflow.tracking.fluent: Experiment with name 'LightGBM' does not exist. Creating a new experiment.\n" + ] + }, + { + "data": { + "text/plain": [ + "<Experiment: artifact_location='/Users/arham/Downloads/Projects/03-Experiments/mlruns/4', creation_time=1714075083201, experiment_id='4', last_update_time=1714075083201, lifecycle_stage='active', name='LightGBM', tags={}>" + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import mlflow\n", + "# Set the MLflow tracking URI to a new SQLite URI\n", + "mlflow.set_tracking_uri(\"sqlite:///new_mlflow.db\")\n", + "mlflow.set_experiment(\"LightGBM\")" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "from sklearn.model_selection import train_test_split\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "import numpy as np\n", + "from sklearn.preprocessing import MinMaxScaler\n", + "from sklearn.preprocessing import PolynomialFeatures\n", + "import lightgbm as lgb\n", + "from sklearn.metrics import accuracy_score\n", + "\n", + "def load_data(path):\n", + " df = pd.read_csv(path)\n", + " train_df, test_df = train_test_split(df, test_size=0.35, random_state=42)\n", + " train_df, val_df, = train_test_split(train_df, test_size=0.20, random_state=42)\n", + " train_df = train_df.drop(['id'], axis=1).drop_duplicates().reset_index(drop=True)\n", + " test_df = test_df.drop(['id'], axis=1).drop_duplicates().reset_index(drop=True)\n", + " val_df = val_df.drop(['id'], axis=1).drop_duplicates().reset_index(drop=True)\n", + " return train_df, val_df, test_df\n", + "\n", + "def encode_target(train):\n", + " target_key = {'Insufficient_Weight': 0, 'Normal_Weight': 1, 'Overweight_Level_I': 2, 'Overweight_Level_II': 3, 'Obesity_Type_I': 4,'Obesity_Type_II' : 5, 'Obesity_Type_III': 6}\n", + " train['NObeyesdad'] = train['NObeyesdad'].map(target_key)\n", + " return train\n", + "\n", + "def make_gender_binary(train):\n", + " train['Gender'] = train['Gender'].map({'Male':0, 'Female':1})\n", + "\n", + "def datatypes(train):\n", + " train['Weight'] = train['Weight'].astype(float)\n", + " train['Age'] = train['Age'].astype(float)\n", + " train['Height'] = train['Height'].astype(float)\n", + " return train\n", + "\n", + "# def age_binning(train_df):\n", + "# train_df['Age_Group'] = pd.cut(train_df['Age'], bins=[0, 20, 30, 40, 50, train_df['Age'].max()], labels=['0-20', '21-30', '31-40', '41-50', '50+'])\n", + "# return train_df\n", + "\n", + "def age_binning(df):\n", + " age_groups = []\n", + " for age in df['Age']:\n", + " if age <= 20:\n", + " age_group = 1\n", + " elif age <= 30:\n", + " age_group = 2\n", + " elif age <= 40:\n", + " age_group = 3\n", + " elif age <= 50:\n", + " age_group = 4\n", + " else:\n", + " age_group = 5\n", + " age_groups.append(age_group)\n", + " df['Age_Group'] = age_groups\n", + " return df\n", + "\n", + "def age_scaling_log(train_df):\n", + " train_df['Age'] = train_df['Age'].astype(float)\n", + " train_df['Log_Age'] = np.log1p(train_df['Age'])\n", + " return train_df\n", + "\n", + "def age_scaling_minmax(train_df):\n", + " train_df['Age'] = train_df['Age'].astype(float)\n", + " scaler_age = MinMaxScaler()\n", + " train_df['Scaled_Age'] = scaler_age.fit_transform(train_df['Age'].values.reshape(-1, 1))\n", + " return train_df, scaler_age\n", + "\n", + "def weight_scaling_log(train_df):\n", + " train_df['Weight'] = train_df['Weight'].astype(float)\n", + " train_df['Log_Weight'] = np.log1p(train_df['Weight'])\n", + " return train_df\n", + "\n", + "def weight_scaling_minmax(train_df):\n", + " train_df['Weight'] = train_df['Weight'].astype(float)\n", + " scaler_weight = MinMaxScaler()\n", + " train_df['Scaled_Weight'] = scaler_weight.fit_transform(train_df['Weight'].values.reshape(-1, 1))\n", + " return train_df, scaler_weight\n", + "\n", + "def height_scaling_log(train_df):\n", + " train_df['Log_Height'] = np.log1p(train_df['Height'])\n", + " return train_df\n", + "\n", + "def height_scaling_minmax(train_df):\n", + " scaler_height = MinMaxScaler()\n", + " train_df['Scaled_Height'] = scaler_height.fit_transform(train_df['Height'].values.reshape(-1, 1))\n", + " return train_df, scaler_height\n", + "\n", + "def make_gender_binary(train):\n", + " train['Gender'] = train['Gender'].map({'Female':1, 'Male':0})\n", + " return train\n", + "\n", + "def fix_binary_columns(train):\n", + " Binary_Cols = ['family_history_with_overweight','FAVC', 'SCC','SMOKE']\n", + " # if yes then 1 else 0\n", + " for col in Binary_Cols:\n", + " train[col] = train[col].map({'yes': 1, 'no': 0})\n", + " return train\n", + "\n", + "def freq_cat_cols(train):\n", + " # One hot encoding\n", + " cat_cols = ['CAEC', 'CALC']\n", + " for col in cat_cols:\n", + " train[col] = train[col].map({'no': 0, 'Sometimes': 1, 'Frequently': 2, 'Always': 3})\n", + " return train\n", + "\n", + "def Mtrans(train):\n", + " \"\"\"\n", + " Public_Transportation 8692\n", + " Automobile 1835\n", + " Walking 231\n", + " Motorbike 19\n", + " Bike 16\n", + " \"\"\"\n", + " # train['MTRANS'] = train['MTRANS'].map({'Public_Transportation': 3, 'Automobile': 5, 'Walking': 1, 'Motorbike': 4, 'Bike': 2})\n", + " # dummify column\n", + " train = pd.get_dummies(train, columns=['MTRANS'])\n", + " return train\n", + "\n", + "\n", + "def other_features(train):\n", + " train['BMI'] = train['Weight'] / (train['Height'] ** 2)\n", + " # train['Age'*'Gender'] = train['Age'] * train['Gender']\n", + " polynomial_features = PolynomialFeatures(degree=2)\n", + " X_poly = polynomial_features.fit_transform(train[['Age', 'BMI']])\n", + " poly_features_df = pd.DataFrame(X_poly, columns=['Age^2', 'Age^3', 'BMI^2', 'Age * BMI', 'Age * BMI^2', 'Age^2 * BMI^2'])\n", + " train = pd.concat([train, poly_features_df], axis=1)\n", + " return train\n", + "\n", + "\n", + "def test_pipeline(test, scaler_age, scaler_weight, scaler_height):\n", + " test = datatypes(test)\n", + " test = encode_target(test)\n", + " test = age_binning(test)\n", + " test = age_scaling_log(test)\n", + " test['Scaled_Age'] = scaler_age.transform(test['Age'].values.reshape(-1, 1))\n", + " test = weight_scaling_log(test)\n", + " test['Scaled_Weight'] = scaler_weight.transform(test['Weight'].values.reshape(-1, 1))\n", + " test = height_scaling_log(test)\n", + " test['Scaled_Height'] = scaler_height.transform(test['Height'].values.reshape(-1, 1))\n", + " test = make_gender_binary(test)\n", + " test = fix_binary_columns(test)\n", + " test = freq_cat_cols(test)\n", + " test = Mtrans(test)\n", + " test = other_features(test)\n", + "\n", + " return test\n", + "\n", + "def train_model(params, X_train, y_train):\n", + " lgb_train = lgb.Dataset(X_train, y_train)\n", + " model = lgb.train(params, lgb_train, num_boost_round=1000)\n", + " return model\n", + "\n", + "def evaluate_model(model, X_val, y_val):\n", + " y_pred = model.predict(X_val)\n", + " y_pred = [np.argmax(y) for y in y_pred]\n", + " accuracy = accuracy_score(y_val, y_pred)\n", + " return accuracy\n", + "\n", + "def objective(trial, X_train, y_train):\n", + " params = {\n", + " 'objective': 'multiclass',\n", + " 'num_class': 7,\n", + " 'metric': 'multi_logloss',\n", + " 'boosting_type': 'gbdt',\n", + " 'learning_rate': trial.suggest_loguniform('learning_rate', 0.005, 0.5),\n", + " 'num_leaves': trial.suggest_int('num_leaves', 10, 1000),\n", + " 'max_depth': trial.suggest_int('max_depth', -1, 20),\n", + " 'bagging_fraction': trial.suggest_uniform('bagging_fraction', 0.6, 0.95),\n", + " 'feature_fraction': trial.suggest_uniform('feature_fraction', 0.6, 0.95),\n", + " 'verbosity': -1\n", + " }\n", + "\n", + " n_splits = 5\n", + " kf = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=42)\n", + " scores = []\n", + "\n", + " for train_index, val_index in kf.split(X_train, y_train):\n", + " X_tr, X_val = X_train.iloc[train_index], X_train.iloc[val_index]\n", + " y_tr, y_val = y_train.iloc[train_index], y_train.iloc[val_index]\n", + "\n", + " model = train_model(params, X_tr, y_tr)\n", + " accuracy = evaluate_model(model, X_val, y_val)\n", + " scores.append(accuracy)\n", + "\n", + " return np.mean(scores)\n", + "\n", + "def optimize_hyperparameters(X_train, y_train, n_trials=2):\n", + " study = optuna.create_study(direction='maximize')\n", + " study.optimize(lambda trial: objective(trial, X_train, y_train), n_trials=n_trials)\n", + " return study.best_params\n", + "\n", + "def New_Test_Instances_Pipeline(test, scaler_age, scaler_weight, scaler_height):\n", + " test = datatypes(test)\n", + " test = age_binning(test)\n", + " test = age_scaling_log(test)\n", + " test['Scaled_Age'] = scaler_age.transform(test['Age'].values.reshape(-1, 1))\n", + " test = weight_scaling_log(test)\n", + " test['Scaled_Weight'] = scaler_weight.transform(test['Weight'].values.reshape(-1, 1))\n", + " test = height_scaling_log(test)\n", + " test['Scaled_Height'] = scaler_height.transform(test['Height'].values.reshape(-1, 1))\n", + " test = make_gender_binary(test)\n", + " test = fix_binary_columns(test)\n", + " test = freq_cat_cols(test)\n", + " test = Mtrans(test)\n", + " test = other_features(test)\n", + "\n", + " return test" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Experiment" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Target Drift For Each Class [0.004943133623686147, 0.011990707821925795, -0.0087675011457998, -0.001077949504617301, -0.017190035106736085, -0.00032756263090533144, 0.01042920694244659]\n", + "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n", + "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001163 seconds.\n", + "You can set `force_row_wise=true` to remove the overhead.\n", + "And if memory is not enough, you can set `force_col_wise=true`.\n", + "[LightGBM] [Info] Total Bins 3576\n", + "[LightGBM] [Info] Number of data points in the train set: 10793, number of used features: 25\n", + "[LightGBM] [Info] Start training from score -2.103541\n", + "[LightGBM] [Info] Start training from score -1.893390\n", + "[LightGBM] [Info] Start training from score -2.159762\n", + "[LightGBM] [Info] Start training from score -2.113461\n", + "[LightGBM] [Info] Start training from score -1.974767\n", + "[LightGBM] [Info] Start training from score -1.867272\n", + "[LightGBM] [Info] Start training from score -1.619963\n", + "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n", + "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000883 seconds.\n", + "You can set `force_row_wise=true` to remove the overhead.\n", + "And if memory is not enough, you can set `force_col_wise=true`.\n", + "[LightGBM] [Info] Total Bins 3576\n", + "[LightGBM] [Info] Number of data points in the train set: 8634, number of used features: 25\n", + "[LightGBM] [Info] Start training from score -2.104065\n", + "[LightGBM] [Info] Start training from score -1.893344\n", + "[LightGBM] [Info] Start training from score -2.159716\n", + "[LightGBM] [Info] Start training from score -2.113607\n", + "[LightGBM] [Info] Start training from score -1.974220\n", + "[LightGBM] [Info] Start training from score -1.867526\n", + "[LightGBM] [Info] Start training from score -1.619799\n", + "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n", + "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n", + "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001080 seconds.\n", + "You can set `force_row_wise=true` to remove the overhead.\n", + "And if memory is not enough, you can set `force_col_wise=true`.\n", + "[LightGBM] [Info] Total Bins 3573\n", + "[LightGBM] [Info] Number of data points in the train set: 8634, number of used features: 25\n", + "[LightGBM] [Info] Start training from score -2.104065\n", + "[LightGBM] [Info] Start training from score -1.893344\n", + "[LightGBM] [Info] Start training from score -2.159716\n", + "[LightGBM] [Info] Start training from score -2.112648\n", + "[LightGBM] [Info] Start training from score -1.974220\n", + "[LightGBM] [Info] Start training from score -1.867526\n", + "[LightGBM] [Info] Start training from score -1.620385\n", + "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n", + "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n", + "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000459 seconds.\n", + "You can set `force_row_wise=true` to remove the overhead.\n", + "And if memory is not enough, you can set `force_col_wise=true`.\n", + "[LightGBM] [Info] Total Bins 3572\n", + "[LightGBM] [Info] Number of data points in the train set: 8634, number of used features: 25\n", + "[LightGBM] [Info] Start training from score -2.103115\n", + "[LightGBM] [Info] Start training from score -1.893344\n", + "[LightGBM] [Info] Start training from score -2.159716\n", + "[LightGBM] [Info] Start training from score -2.113607\n", + "[LightGBM] [Info] Start training from score -1.975054\n", + "[LightGBM] [Info] Start training from score -1.867526\n", + "[LightGBM] [Info] Start training from score -1.619799\n", + "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n", + "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001021 seconds.\n", + "You can set `force_row_wise=true` to remove the overhead.\n", + "And if memory is not enough, you can set `force_col_wise=true`.\n", + "[LightGBM] [Info] Total Bins 3571\n", + "[LightGBM] [Info] Number of data points in the train set: 8635, number of used features: 25\n", + "[LightGBM] [Info] Start training from score -2.103231\n", + "[LightGBM] [Info] Start training from score -1.893459\n", + "[LightGBM] [Info] Start training from score -2.159832\n", + "[LightGBM] [Info] Start training from score -2.113723\n", + "[LightGBM] [Info] Start training from score -1.975170\n", + "[LightGBM] [Info] Start training from score -1.866892\n", + "[LightGBM] [Info] Start training from score -1.619915\n", + "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n", + "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000919 seconds.\n", + "You can set `force_row_wise=true` to remove the overhead.\n", + "And if memory is not enough, you can set `force_col_wise=true`.\n", + "[LightGBM] [Info] Total Bins 3575\n", + "[LightGBM] [Info] Number of data points in the train set: 8635, number of used features: 25\n", + "[LightGBM] [Info] Start training from score -2.103231\n", + "[LightGBM] [Info] Start training from score -1.893459\n", + "[LightGBM] [Info] Start training from score -2.159832\n", + "[LightGBM] [Info] Start training from score -2.113723\n", + "[LightGBM] [Info] Start training from score -1.975170\n", + "[LightGBM] [Info] Start training from score -1.866892\n", + "[LightGBM] [Info] Start training from score -1.619915\n", + "[LightGBM] [Warning] No further splits with positive gain, best gain: -inf\n", + "\n", + "Accuracy: 0.904845733345687\n", + "Precision: 0.9046557231546489\n", + "Recall: 0.904845733345687\n", + "F1: 0.9046297258523301\n", + "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n", + "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001173 seconds.\n", + "You can set `force_row_wise=true` to remove the overhead.\n", + "And if memory is not enough, you can set `force_col_wise=true`.\n", + "[LightGBM] [Info] Total Bins 3576\n", + "[LightGBM] [Info] Number of data points in the train set: 10793, number of used features: 25\n", + "[LightGBM] [Info] Start training from score -2.103541\n", + "[LightGBM] [Info] Start training from score -1.893390\n", + "[LightGBM] [Info] Start training from score -2.159762\n", + "[LightGBM] [Info] Start training from score -2.113461\n", + "[LightGBM] [Info] Start training from score -1.974767\n", + "[LightGBM] [Info] Start training from score -1.867272\n", + "[LightGBM] [Info] Start training from score -1.619963\n", + "Recall for class 0: 0.9367088607594937\n", + "Recall for class 1: 0.9117647058823529\n", + "Recall for class 2: 0.755223880597015\n", + "Recall for class 3: 0.8267477203647416\n", + "Recall for class 4: 0.8669833729216152\n", + "Recall for class 5: 0.9617224880382775\n", + "Recall for class 6: 0.9960474308300395\n" + ] + } + ], + "source": [ + "path = '/Users/arham/Downloads/Projects/01-Dataset/01-Data-for-model-building/train.csv'\n", + "train_df, val_df, test_df = load_data(path)\n", + "\n", + "# train test val pipeline\n", + "train_df = datatypes(train_df)\n", + "train_df = encode_target(train_df)\n", + "train_df = age_binning(train_df)\n", + "train_df, scaler_age = age_scaling_minmax(train_df)\n", + "train_df = age_scaling_log(train_df)\n", + "train_df, scaler_weight = weight_scaling_minmax(train_df)\n", + "train_df = weight_scaling_log(train_df)\n", + "train_df, scaler_height = height_scaling_minmax(train_df)\n", + "train_df = height_scaling_log(train_df)\n", + "train_df = make_gender_binary(train_df)\n", + "train_df = fix_binary_columns(train_df)\n", + "train_df = freq_cat_cols(train_df)\n", + "train_df = Mtrans(train_df)\n", + "train_df = other_features(train_df)\n", + "val_df = test_pipeline(val_df, scaler_age, scaler_weight, scaler_height)\n", + "test_df = test_pipeline(test_df, scaler_age, scaler_weight, scaler_height)\n", + "\n", + "\n", + "# target & predictors\n", + "Target = 'NObeyesdad'\n", + "features = ['Gender', 'Age', 'Height', 'Weight', 'family_history_with_overweight',\n", + " 'FAVC', 'FCVC', 'NCP', 'CAEC', 'SMOKE', 'CH2O', 'SCC', 'FAF', 'TUE',\n", + " 'CALC', 'Age_Group', \n", + " 'MTRANS_Automobile', 'MTRANS_Bike', 'MTRANS_Motorbike',\n", + " 'MTRANS_Public_Transportation', 'MTRANS_Walking', 'BMI', 'Age^2',\n", + " 'Age^3', 'BMI^2', 'Age * BMI', 'Age * BMI^2', 'Age^2 * BMI^2'] \n", + " #'Scaled_Age', 'Log_Age', 'Scaled_Weight', 'Log_Weight', 'Scaled_Height', 'Log_Height',\n", + "\n", + "X_train = train_df[features]\n", + "y_train = train_df[Target]\n", + "X_val = val_df[features]\n", + "y_val = val_df[Target]\n", + "X_test = test_df[features]\n", + "y_test = test_df[Target]\n", + "\n", + "\n", + "lgb_train = lgb.Dataset(X_train, y_train)\n", + "params = {\n", + " 'objective': 'multiclass',\n", + " 'num_class': 7,\n", + " 'metric': 'multi_logloss',\n", + "}\n", + "\n", + "from sklearn.metrics import precision_recall_fscore_support, accuracy_score\n", + "import mlflow\n", + "import lightgbm as lgb\n", + "from lightgbm import LGBMClassifier\n", + "from sklearn.model_selection import cross_val_predict\n", + "\n", + "mlflow.sklearn.autolog(disable=True)\n", + "\n", + "with mlflow.start_run(run_name=\"LGBM_without_FE_v2\"):\n", + " class_counts_train = [y_train[y_train == i].count() / y_train.count() for i in range(7)]\n", + " class_counts_val = [y_val[y_val == i].count() / y_val.count() for i in range(7)]\n", + " target_drift = [(train_count - val_count) for train_count, val_count in zip(class_counts_train, class_counts_val)]\n", + " print(f\"Target Drift For Each Class {target_drift}\")\n", + " mlflow.log_params({'Target_Drift_' + str(i): freq for i, freq in enumerate(target_drift)})\n", + "\n", + " model = LGBMClassifier(**params) # Assuming you have your parameters defined somewhere\n", + " model.fit(X_train, y_train) # Fit the model on training data\n", + "\n", + " # CV predictions of LightGBM\n", + " cv_predictions = cross_val_predict(model, X_train, y_train, cv=5)\n", + " accuracy_lgbm = accuracy_score(y_train, cv_predictions)\n", + " \n", + " # Compute precision, recall, and F1-score\n", + " precision_lgbm, recall_lgbm, f1_lgbm, _ = precision_recall_fscore_support(y_train, cv_predictions, average='weighted')\n", + " \n", + " print(\"\\nAccuracy:\", accuracy_lgbm)\n", + " print(\"Precision:\", precision_lgbm)\n", + " print(\"Recall:\", recall_lgbm)\n", + " print(\"F1:\", f1_lgbm)\n", + " \n", + " mlflow.log_metric('accuracy', accuracy_lgbm)\n", + " mlflow.log_metric('precision', precision_lgbm)\n", + " mlflow.log_metric('recall', recall_lgbm)\n", + " mlflow.log_metric('f1', f1_lgbm)\n", + "\n", + " model.fit(X_train, y_train)\n", + " y_val_pred_lgbm = model.predict(X_val)\n", + " \n", + " # Compute precision, recall, and F1-score per class\n", + " precision_per_class, recall_per_class, f1_per_class, support_per_class = precision_recall_fscore_support(y_val, y_val_pred_lgbm, average=None)\n", + " for i in range(len(recall_per_class)):\n", + " print(f\"Recall for class {i}: {recall_per_class[i]}\")\n", + " mlflow.log_metric(f'recall_class_{i}', recall_per_class[i])\n", + "\n", + " mlflow.lightgbm.log_model(model, 'model')\n", + " mlflow.set_tag('experiments', 'Arham A.')\n", + " mlflow.set_tag('model_name', 'LGBM')\n", + " mlflow.set_tag('preprocessing', 'Yes')\n" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": {}, + "outputs": [], + "source": [ + "# train_df, val_df, test_df = load_data(path)\n", + "\n", + "\n", + "# X_val = val_df[features]\n", + "# y_val = val_df[Target]\n", + "# y_pred = model.predict(X_val, num_iteration=model.best_iteration)\n", + "# # y_pred to a dataframe\n", + "# y_pred = pd.DataFrame(y_pred, columns=['Insufficient_Weight', 'Normal_Weight', 'Overweight_Level_I', 'Overweight_Level_II', 'Obesity_Type_I', 'Obesity_Type_II', 'Obesity_Type_III'])\n", + "# # add prefix to columns \"prob_lgbm_\"\n", + "# y_pred = y_pred.add_prefix('prob_lgbm_')\n", + "# # add to X_val\n", + "# X_val = pd.concat([X_val, y_pred], axis=1)\n", + "# # export as stack_aid_lgbm.csv\n", + "# X_val.to_csv('stack_aid_lgbm.csv', index=False)" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "data": { + "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>Gender</th>\n", + " <th>Age</th>\n", + " <th>Height</th>\n", + " <th>Weight</th>\n", + " <th>family_history_with_overweight</th>\n", + " <th>FAVC</th>\n", + " <th>FCVC</th>\n", + " <th>NCP</th>\n", + " <th>CAEC</th>\n", + " <th>SMOKE</th>\n", + " <th>CH2O</th>\n", + " <th>SCC</th>\n", + " <th>FAF</th>\n", + " <th>TUE</th>\n", + " <th>CALC</th>\n", + " <th>Age_Group</th>\n", + " <th>MTRANS_Automobile</th>\n", + " <th>MTRANS_Bike</th>\n", + " <th>MTRANS_Motorbike</th>\n", + " <th>MTRANS_Public_Transportation</th>\n", + " <th>MTRANS_Walking</th>\n", + " <th>BMI</th>\n", + " <th>Age^2</th>\n", + " <th>Age^3</th>\n", + " <th>BMI^2</th>\n", + " <th>Age * BMI</th>\n", + " <th>Age * BMI^2</th>\n", + " <th>Age^2 * BMI^2</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>0</th>\n", + " <td>1</td>\n", + " <td>21.000000</td>\n", + " <td>1.550000</td>\n", + " <td>51.000000</td>\n", + " <td>0</td>\n", + " <td>1</td>\n", + " <td>3.0</td>\n", + " <td>1.0</td>\n", + " <td>2</td>\n", + " <td>0</td>\n", + " <td>2.000000</td>\n", + " <td>0</td>\n", + " <td>0.000000</td>\n", + " <td>0.000000</td>\n", + " <td>0</td>\n", + " <td>21-30</td>\n", + " <td>False</td>\n", + " <td>False</td>\n", + " <td>False</td>\n", + " <td>True</td>\n", + " <td>False</td>\n", + " <td>21.227888</td>\n", + " <td>1.0</td>\n", + " <td>21.000000</td>\n", + " <td>21.227888</td>\n", + " <td>441.000000</td>\n", + " <td>445.785640</td>\n", + " <td>450.623213</td>\n", + " </tr>\n", + " <tr>\n", + " <th>1</th>\n", + " <td>0</td>\n", + " <td>20.000000</td>\n", + " <td>1.700000</td>\n", + " <td>80.000000</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>2.0</td>\n", + " <td>3.0</td>\n", + " <td>1</td>\n", + " <td>0</td>\n", + " <td>2.000000</td>\n", + " <td>0</td>\n", + " <td>2.000000</td>\n", + " <td>1.000000</td>\n", + " <td>1</td>\n", + " <td>0-20</td>\n", + " <td>False</td>\n", + " <td>False</td>\n", + " <td>False</td>\n", + " <td>True</td>\n", + " <td>False</td>\n", + " <td>27.681661</td>\n", + " <td>1.0</td>\n", + " <td>20.000000</td>\n", + " <td>27.681661</td>\n", + " <td>400.000000</td>\n", + " <td>553.633218</td>\n", + " <td>766.274350</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>1</td>\n", + " <td>18.000000</td>\n", + " <td>1.600000</td>\n", + " <td>60.000000</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>2.0</td>\n", + " <td>3.0</td>\n", + " <td>1</td>\n", + " <td>0</td>\n", + " <td>2.000000</td>\n", + " <td>0</td>\n", + " <td>1.000000</td>\n", + " <td>1.000000</td>\n", + " <td>0</td>\n", + " <td>0-20</td>\n", + " <td>False</td>\n", + " <td>False</td>\n", + " <td>False</td>\n", + " <td>False</td>\n", + " <td>True</td>\n", + " <td>23.437500</td>\n", + " <td>1.0</td>\n", + " <td>18.000000</td>\n", + " <td>23.437500</td>\n", + " <td>324.000000</td>\n", + " <td>421.875000</td>\n", + " <td>549.316406</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>1</td>\n", + " <td>26.000000</td>\n", + " <td>1.632983</td>\n", + " <td>111.720238</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>3.0</td>\n", + " <td>3.0</td>\n", + " <td>1</td>\n", + " <td>0</td>\n", + " <td>2.559750</td>\n", + " <td>0</td>\n", + " <td>0.000000</td>\n", + " <td>0.396972</td>\n", + " <td>1</td>\n", + " <td>21-30</td>\n", + " <td>False</td>\n", + " <td>False</td>\n", + " <td>False</td>\n", + " <td>True</td>\n", + " <td>False</td>\n", + " <td>41.895611</td>\n", + " <td>1.0</td>\n", + " <td>26.000000</td>\n", + " <td>41.895611</td>\n", + " <td>676.000000</td>\n", + " <td>1089.285877</td>\n", + " <td>1755.242193</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>1</td>\n", + " <td>21.682636</td>\n", + " <td>1.748524</td>\n", + " <td>133.845064</td>\n", + " <td>1</td>\n", + " <td>1</td>\n", + " <td>3.0</td>\n", + " <td>3.0</td>\n", + " <td>1</td>\n", + " <td>0</td>\n", + " <td>2.843777</td>\n", + " <td>0</td>\n", + " <td>1.427037</td>\n", + " <td>0.849236</td>\n", + " <td>1</td>\n", + " <td>21-30</td>\n", + " <td>False</td>\n", + " <td>False</td>\n", + " <td>False</td>\n", + " <td>True</td>\n", + " <td>False</td>\n", + " <td>43.778327</td>\n", + " <td>1.0</td>\n", + " <td>21.682636</td>\n", + " <td>43.778327</td>\n", + " <td>470.136704</td>\n", + " <td>949.229536</td>\n", + " <td>1916.541944</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "</div>" + ], + "text/plain": [ + " Gender Age Height Weight family_history_with_overweight \\\n", + "0 1 21.000000 1.550000 51.000000 0 \n", + "1 0 20.000000 1.700000 80.000000 1 \n", + "2 1 18.000000 1.600000 60.000000 1 \n", + "3 1 26.000000 1.632983 111.720238 1 \n", + "4 1 21.682636 1.748524 133.845064 1 \n", + "\n", + " FAVC FCVC NCP CAEC SMOKE CH2O SCC FAF TUE CALC \\\n", + "0 1 3.0 1.0 2 0 2.000000 0 0.000000 0.000000 0 \n", + "1 1 2.0 3.0 1 0 2.000000 0 2.000000 1.000000 1 \n", + "2 1 2.0 3.0 1 0 2.000000 0 1.000000 1.000000 0 \n", + "3 1 3.0 3.0 1 0 2.559750 0 0.000000 0.396972 1 \n", + "4 1 3.0 3.0 1 0 2.843777 0 1.427037 0.849236 1 \n", + "\n", + " Age_Group MTRANS_Automobile MTRANS_Bike MTRANS_Motorbike \\\n", + "0 21-30 False False False \n", + "1 0-20 False False False \n", + "2 0-20 False False False \n", + "3 21-30 False False False \n", + "4 21-30 False False False \n", + "\n", + " MTRANS_Public_Transportation MTRANS_Walking BMI Age^2 Age^3 \\\n", + "0 True False 21.227888 1.0 21.000000 \n", + "1 True False 27.681661 1.0 20.000000 \n", + "2 False True 23.437500 1.0 18.000000 \n", + "3 True False 41.895611 1.0 26.000000 \n", + "4 True False 43.778327 1.0 21.682636 \n", + "\n", + " BMI^2 Age * BMI Age * BMI^2 Age^2 * BMI^2 \n", + "0 21.227888 441.000000 445.785640 450.623213 \n", + "1 27.681661 400.000000 553.633218 766.274350 \n", + "2 23.437500 324.000000 421.875000 549.316406 \n", + "3 41.895611 676.000000 1089.285877 1755.242193 \n", + "4 43.778327 470.136704 949.229536 1916.541944 " + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# show all columns\n", + "pd.set_option('display.max_columns', None)\n", + "X_train.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Testing Single Instance For Architecture Development" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": {}, + "outputs": [], + "source": [ + "input_data = {\n", + " \"id\": 6204,\n", + " \"Gender\": \"Female\",\n", + " \"Age\": 23.0,\n", + " \"Height\": 1.581527,\n", + " \"Weight\": 78.089575,\n", + " \"family_history_with_overweight\": \"yes\",\n", + " \"FAVC\": \"yes\",\n", + " \"FCVC\": 2.0,\n", + " \"NCP\": 2.070033,\n", + " \"CAEC\": \"Sometimes\",\n", + " \"SMOKE\": \"no\", \n", + " \"CH2O\": 2.953192,\n", + " \"SCC\": \"no\",\n", + " \"FAF\": 0.118271,\n", + " \"TUE\": 0.0,\n", + " \"CALC\": \"no\",\n", + " \"MTRANS\": \"Public_Transportation\"\n", + " \n", + "}\n", + "\n", + "input_df = pd.DataFrame([input_data])\n", + "input_df = New_Test_Instances_Pipeline(input_df, scaler_age, scaler_weight, scaler_height)\n", + "\n", + "# X input to have same columns as features\n", + "X_input = pd.DataFrame(columns=features)\n", + "# if input df does not have a column that is in features, add it with 0s at the same position\n", + "for col in features:\n", + " if col not in input_df.columns:\n", + " if col in ['MTRANS_Automobile', 'MTRANS_Bike', 'MTRANS_Motorbike', 'MTRANS_Public_Transportation', 'MTRANS_Walking']:\n", + " X_input[col] = False\n", + " else:\n", + " X_input[col] = 0\n", + " else:\n", + " X_input[col] = input_df[col]\n", + " # if MTRANS_Automobile, MTRANS_Bike, MTRANS_Motorbike, MTRANS_Public_Transportation, MTRANS_Walking are zero, make them False\n", + " \n", + "y_pred_proba = model.predict(X_input)\n", + "y_pred = np.argmax(y_pred_proba)\n", + "\n", + "y_pred" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "4" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "DataScience", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.13" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}