Move function to helper.py

machine_learning/helper.py

@@ -1,6 +1,13 @@
 from pathlib import Path
+from sklearn import linear_model, svm, kernel_ridge, gaussian_process, ensemble
+from sklearn.model_selection import LeaveOneGroupOut, cross_val_score, cross_validate
+from sklearn.metrics import mean_squared_error, r2_score
+from sklearn.impute import SimpleImputer
+from sklearn.dummy import DummyRegressor
+from xgboost import XGBRegressor
 
 import pandas as pd
+import numpy as np
 
 
 def safe_outer_merge_on_index(left: pd.DataFrame, right: pd.DataFrame) -> pd.DataFrame:
@@ -55,3 +62,199 @@ def construct_full_path(folder: Path, filename_prefix: str, data_type: str) -> P
     export_filename = filename_prefix + "_" + data_type + ".csv"
     full_path = folder / export_filename
     return full_path
+
+def insert_row(df, row):
+    return pd.concat([df, pd.DataFrame([row], columns=df.columns)], ignore_index=True)
+
+def run_all_models(input_csv):
+    # Prepare data
+    model_input = pd.read_csv(input_csv)
+    model_input.dropna(axis=1, how="all", inplace=True)
+    model_input.dropna(axis=0, how="any", subset=["target"], inplace=True)
+
+    index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
+    model_input.set_index(index_columns, inplace=True)
+
+    data_x, data_y, data_groups = model_input.drop(["target", "pid"], axis=1), model_input["target"], model_input["pid"]
+
+    categorical_feature_colnames = ["gender", "startlanguage"]
+    categorical_features = data_x[categorical_feature_colnames].copy()
+    mode_categorical_features = categorical_features.mode().iloc[0]
+    # fillna with mode
+    categorical_features = categorical_features.fillna(mode_categorical_features)
+    # one-hot encoding
+    categorical_features = categorical_features.apply(lambda col: col.astype("category"))
+    if not categorical_features.empty:
+        categorical_features = pd.get_dummies(categorical_features)
+
+    numerical_features = data_x.drop(categorical_feature_colnames, axis=1)
+
+    train_x = pd.concat([numerical_features, categorical_features], axis=1)
+    imputer = SimpleImputer(missing_values=np.nan, strategy='mean')
+    train_x_imputed = imputer.fit_transform(train_x)
+
+    # Prepare cross validation
+    logo = LeaveOneGroupOut()
+    logo.get_n_splits(
+        train_x,
+        data_y,
+        groups=data_groups,
+    )
+    scores = pd.DataFrame(columns=["method", "median", "max"])
+
+    # Validate models
+    lin_reg_rapids = linear_model.LinearRegression()
+    lin_reg_scores = cross_val_score(
+        lin_reg_rapids,
+        X=train_x_imputed,
+        y=data_y,
+        groups=data_groups,
+        cv=logo,
+        n_jobs=-1,
+        scoring='r2'
+    )
+    print("Linear regression:")
+    print(np.median(lin_reg_scores))
+    scores = insert_row(scores, ["Linear regression",np.median(lin_reg_scores),np.max(lin_reg_scores)])
+
+    ridge_reg = linear_model.Ridge(alpha=.5)
+    ridge_reg_scores = cross_val_score(
+        ridge_reg,
+        X=train_x_imputed,
+        y=data_y,
+        groups=data_groups,
+        cv=logo,
+        n_jobs=-1,
+        scoring="r2"
+    )
+    print("Ridge regression")
+    print(np.median(ridge_reg_scores))
+    scores = insert_row(scores, ["Ridge regression",np.median(ridge_reg_scores),np.max(ridge_reg_scores)])
+
+    lasso_reg = linear_model.Lasso(alpha=0.1)
+    lasso_reg_score = cross_val_score(
+        lasso_reg,
+        X=train_x_imputed,
+        y=data_y,
+        groups=data_groups,
+        cv=logo,
+        n_jobs=-1,
+        scoring="r2"
+    )
+    print("Lasso regression")
+    print(np.median(lasso_reg_score))
+    scores = insert_row(scores, ["Lasso regression",np.median(lasso_reg_score),np.max(lasso_reg_score)])
+
+    bayesian_ridge_reg = linear_model.BayesianRidge()
+    bayesian_ridge_reg_score = cross_val_score(
+        bayesian_ridge_reg,
+        X=train_x_imputed,
+        y=data_y,
+        groups=data_groups,
+        cv=logo,
+        n_jobs=-1,
+        scoring="r2"
+    )
+    print("Bayesian Ridge")
+    print(np.median(bayesian_ridge_reg_score))
+    scores = insert_row(scores, ["Bayesian Ridge",np.median(bayesian_ridge_reg_score),np.max(bayesian_ridge_reg_score)])
+
+    ransac_reg = linear_model.RANSACRegressor()
+    ransac_reg_score = cross_val_score(
+        ransac_reg,
+        X=train_x_imputed,
+        y=data_y,
+        groups=data_groups,
+        cv=logo,
+        n_jobs=-1,
+        scoring="r2"
+    )
+    print("RANSAC (outlier robust regression)")
+    print(np.median(ransac_reg_score))
+    scores = insert_row(scores, ["RANSAC",np.median(ransac_reg_score),np.max(ransac_reg_score)])
+
+    svr = svm.SVR()
+    svr_score = cross_val_score(
+        svr,
+        X=train_x_imputed,
+        y=data_y,
+        groups=data_groups,
+        cv=logo,
+        n_jobs=-1,
+        scoring="r2"
+    )
+    print("Support vector regression")
+    print(np.median(svr_score))
+    scores = insert_row(scores, ["Support vector regression",np.median(svr_score),np.max(svr_score)])
+
+    kridge = kernel_ridge.KernelRidge()
+    kridge_score = cross_val_score(
+        kridge,
+        X=train_x_imputed,
+        y=data_y,
+        groups=data_groups,
+        cv=logo,
+        n_jobs=-1,
+        scoring="r2"
+    )
+    print("Kernel Ridge regression")
+    print(np.median(kridge_score))
+    scores = insert_row(scores, ["Kernel Ridge regression",np.median(kridge_score),np.max(kridge_score)])
+
+    gpr = gaussian_process.GaussianProcessRegressor()
+    gpr_score = cross_val_score(
+        gpr,
+        X=train_x_imputed,
+        y=data_y,
+        groups=data_groups,
+        cv=logo,
+        n_jobs=-1,
+        scoring="r2"
+    )
+    print("Gaussian Process Regression")
+    print(np.median(gpr_score))
+    scores = insert_row(scores, ["Gaussian Process Regression",np.median(gpr_score),np.max(gpr_score)])
+
+    rfr = ensemble.RandomForestRegressor(max_features=0.3, n_jobs=-1)
+    rfr_score = cross_val_score(
+        rfr,
+        X=train_x_imputed,
+        y=data_y,
+        groups=data_groups,
+        cv=logo,
+        n_jobs=-1,
+        scoring="r2"
+    )
+    print("Random Forest Regression")
+    print(np.median(rfr_score))
+    scores = insert_row(scores, ["Random Forest Regression",np.median(rfr_score),np.max(rfr_score)])
+
+    xgb = XGBRegressor()
+    xgb_score = cross_val_score(
+        xgb,
+        X=train_x_imputed,
+        y=data_y,
+        groups=data_groups,
+        cv=logo,
+        n_jobs=-1,
+        scoring="r2"
+    )
+    print("XGBoost Regressor")
+    print(np.median(xgb_score))
+    scores = insert_row(scores, ["XGBoost Regressor",np.median(xgb_score),np.max(xgb_score)])
+
+    ada = ensemble.AdaBoostRegressor()
+    ada_score = cross_val_score(
+        ada,
+        X=train_x_imputed,
+        y=data_y,
+        groups=data_groups,
+        cv=logo,
+        n_jobs=-1,
+        scoring="r2"
+    )
+    print("ADA Boost Regressor")
+    print(np.median(ada_score))
+    scores = insert_row(scores, ["ADA Boost Regressor",np.median(ada_score),np.max(ada_score)])
+
+    return scores