Define classification models method.

machine_learning/helper.py

@@ -1,10 +1,12 @@
 from pathlib import Path
-from sklearn import linear_model, svm, kernel_ridge, gaussian_process, ensemble
+from sklearn import linear_model, svm, kernel_ridge, gaussian_process, ensemble, naive_bayes, neighbors, tree
 from sklearn.model_selection import LeaveOneGroupOut, cross_validate, cross_validate
 from sklearn.metrics import mean_squared_error, r2_score
 from sklearn.impute import SimpleImputer
-from sklearn.dummy import DummyRegressor
+from sklearn.dummy import DummyRegressor, DummyClassifier
-from xgboost import XGBRegressor
+
+from xgboost import XGBRegressor, XGBClassifier
+import xgboost as xg
 
 import pandas as pd
 import numpy as np
@@ -319,3 +321,139 @@ def run_all_regression_models(input_csv):
     scores = pd.concat([scores, scores_df])
 
     return scores
+
+
+def run_all_classification_models(data_x, data_y, data_groups, cv_method):
+    metrics = ['accuracy', 'average_precision', 'recall', 'f1']
+    test_metrics = ["test_" + metric for metric in metrics]
+
+    scores = pd.DataFrame(columns=["method", "max", "mean"])
+
+    dummy_class = DummyClassifier(strategy="most_frequent")
+
+    dummy_score = cross_validate(
+    dummy_class,
+    X=data_x,
+    y=data_y,
+    groups=data_groups,
+    cv=cv_method,
+    n_jobs=-1,
+    error_score='raise',
+    scoring=metrics
+    )
+    print("Dummy")
+
+    scores_df = pd.DataFrame(dummy_score)[test_metrics]
+    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df["method"] = "Dummy"
+    scores = pd.concat([scores, scores_df])
+
+    logistic_regression = linear_model.LogisticRegression()
+
+    log_reg_scores = cross_validate(
+    logistic_regression,
+    X=data_x,
+    y=data_y,
+    groups=data_groups,
+    cv=cv_method,
+    n_jobs=-1,
+    scoring=metrics
+    )
+    print("Logistic regression")
+
+    scores_df = pd.DataFrame(log_reg_scores)[test_metrics]
+    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df["method"] = "logistic_reg"
+    scores = pd.concat([scores, scores_df])
+
+    svc = svm.SVC()
+
+    svc_scores = cross_validate(
+    svc,
+    X=data_x,
+    y=data_y,
+    groups=data_groups,
+    cv=cv_method,
+    n_jobs=-1,
+    scoring=metrics
+    )
+    print("Support Vector Machine")
+
+    scores_df = pd.DataFrame(svc_scores)[test_metrics]
+    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df["method"] = "svc"
+    scores = pd.concat([scores, scores_df])
+
+    gaussian_nb = naive_bayes.GaussianNB()
+    
+    gaussian_nb_scores = cross_validate(
+    gaussian_nb,
+    X=data_x,
+    y=data_y,
+    groups=data_groups,
+    cv=cv_method,
+    n_jobs=-1,
+    scoring=metrics
+    )
+    print("Gaussian Naive Bayes")
+
+    scores_df = pd.DataFrame(gaussian_nb_scores)[test_metrics]
+    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df["method"] = "gaussian_naive_bayes"
+    scores = pd.concat([scores, scores_df])
+
+    sgdc = linear_model.SGDClassifier()
+
+    sgdc_scores = cross_validate(
+    sgdc,
+    X=data_x,
+    y=data_y,
+    groups=data_groups,
+    cv=cv_method,
+    n_jobs=-1,
+    scoring=metrics
+    )
+    print("Stochastic Gradient Descent")
+
+    scores_df = pd.DataFrame(sgdc_scores)[test_metrics]
+    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df["method"] = "stochastic_gradient_descent"
+    scores = pd.concat([scores, scores_df])
+
+    rfc = ensemble.RandomForestClassifier()
+
+    rfc_scores = cross_validate(
+    rfc,
+    X=data_x,
+    y=data_y,
+    groups=data_groups,
+    cv=cv_method,
+    n_jobs=-1,
+    scoring=metrics
+    )
+    print("Random Forest")
+
+    scores_df = pd.DataFrame(rfc_scores)[test_metrics]
+    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df["method"] = "random_forest"
+    scores = pd.concat([scores, scores_df])
+
+    xgb_classifier = XGBClassifier()
+
+    xgb_scores = cross_validate(
+    xgb_classifier,
+    X=data_x,
+    y=data_y,
+    groups=data_groups,
+    cv=cv_method,
+    n_jobs=-1,
+    scoring=metrics
+    )
+    print("XGBoost")
+
+    scores_df = pd.DataFrame(xgb_scores)[test_metrics]
+    scores_df = scores_df.agg(['max', 'mean']).transpose()
+    scores_df["method"] = "xgboost"
+    scores = pd.concat([scores, scores_df])
+
+    return scores