[ADD] machine learning pipeline

src/machine_learning.py

+from src import evaluation_metrics
+from sklearn.svm import SVR
+from sklearn.pipeline import Pipeline
+from sklearn.impute import SimpleImputer
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.feature_selection import SelectKBest
+from sklearn.model_selection import cross_validate
+from sklearn.metrics import make_scorer
+from sklearn.compose import ColumnTransformer
+from inspect import getmembers, isfunction
+
+
+def load_data():
+    # Load dataset (protein and compound features already calculated)
+    # output needs to be transformed to pKd (-log Kd)
+    # return X and y (if it exists)
+    pass
+
+def make_scorers():
+    functions_list = getmembers(evaluation_metrics, isfunction)
+    scorer_list = []
+    for metric_name, func in functions_list:
+        if metric_name == 'rmse':
+            scorer_list.append(make_scorer(func, greater_is_better=False))
+        else:
+            scorer_list.append(make_scorer(func, greater_is_better=True))
+    return scorer_list
+
+X_train, y_train = load_data()
+X_test = load_data()
+# change when we have the real dataset...
+
+# Build pipeline
+# numeric_features =
+numeric_transformer = Pipeline(steps=[('imputer', SimpleImputer(strategy='median')), ('scaler', StandardScaler())])
+# categorical_features =
+categorical_transformer = Pipeline(steps=['imputer', SimpleImputer(strategy='most_frequent'), ('onehot', OneHotEncoder())])
+#binary_features =
+binary_transformer = SimpleImputer(strategy='most_frequent')
+preprocessor = ColumnTransformer(transformers=[('num', numeric_transformer, numeric_features),
+                                               ('cat', categorical_transformer, categorical_features),
+                                               ('bin', binary_transformer, binary_features)])
+
+selector = SelectKBest(k=100) # change k; use another method?
+estimator = SVR() # need to change this easily when testing though
+pipe = Pipeline(steps=[('preprocessor', preprocessor),
+                       ('feature_selector', selector),
+                       ('estimator', estimator)])
+
+# Hyperparameter optimization???
+# ...
+
+# Model Evaluation
+scorer_list = make_scorers()
+cv_results = cross_validate(pipe, X_train, y_train, cv=10, scoring=scorer_list)
+for res in cv_results:
+    print(res+':\n')
+    print(cv_results[res])
+# save cross-validation results to file?
+
+# Prediction
+model = pipe.fit(X_train, y_train)
+predictions = model.predict(X_test)
+
+# Save predictions to csv (use challenge template)
+df = pd.read_csv('../data/round_1_template.csv')
+df = pd.concat([df, predictions], axis=1) # make sure order is maintained in predictions
+df.to_csv('round1_predictions.csv') # change later
\ No newline at end of file