Lec4

data/density/density_test.csv

@@ -0,0 +1,18 @@
+T;Al2O3;TiO2;Density
+30;0;0;1,05696
+55;0;0;1,04158
+25;0,05;0;1,08438
+30;0,05;0;1,08112
+35;0,05;0;1,07781
+40;0,05;0;1,07446
+60;0,05;0;1,06053
+35;0,3;0;1,17459
+65;0,3;0;1,14812
+45;0;0,05;1,07424
+50;0;0,05;1,07075
+55;0;0,05;1,06721
+20;0;0,3;1,22417
+30;0;0,3;1,2131
+40;0;0,3;1,20265
+60;0;0,3;1,18265
+70;0;0,3;1,17261

data/density/density_train.csv

@@ -0,0 +1,39 @@
+T;Al2O3;TiO2;Density
+20;0;0;1,0625
+25;0;0;1,05979
+35;0;0;1,05404
+40;0;0;1,05103
+45;0;0;1,04794
+50;0;0;1,04477
+60;0;0;1,03826
+65;0;0;1,03484
+70;0;0;1,03182
+20;0,05;0;1,08755
+45;0,05;0;1,07105
+50;0,05;0;1,0676
+55;0,05;0;1,06409
+65;0,05;0;1,05691
+70;0,05;0;1,05291
+20;0,3;0;1,18861
+25;0,3;0;1,18389
+30;0,3;0;1,1792
+40;0,3;0;1,17017
+45;0,3;0;1,16572
+50;0,3;0;1,16138
+55;0,3;0;1,15668
+60;0,3;0;1,15233
+70;0,3;0;1,14414
+20;0;0,05;1,09098
+25;0;0,05;1,08775
+30;0;0,05;1,08443
+35;0;0,05;1,08108
+40;0;0,05;1,07768
+60;0;0,05;1,06362
+65;0;0,05;1,05999
+70;0;0,05;1,05601
+25;0;0,3;1,2186
+35;0;0,3;1,20776
+45;0;0,3;1,19759
+50;0;0,3;1,19268
+55;0;0,3;1,18746
+65;0;0,3;1,178

src/transformers.py

@@ -0,0 +1,27 @@
+import numpy as np
+import pandas as pd
+from sklearn.base import BaseEstimator, TransformerMixin
+
+
+class TitanicFeatures(BaseEstimator, TransformerMixin):
+    def __init__(self):
+        pass
+
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X, y=None):
+        def get_title(name) -> str:
+            return name.split(",")[1].split(".")[0].strip()
+
+        def get_cabin_type(cabin) -> str:
+            if pd.isna(cabin):
+                return "unknown"
+            return cabin[0]
+
+        X["Is_married"] = [1 if get_title(name) == "Mrs" else 0 for name in X["Name"]]
+        X["Cabin_type"] = [get_cabin_type(cabin) for cabin in X["Cabin"]]
+        return X
+
+    def get_feature_names_out(self, features_in):
+        return np.append(features_in, ["Is_married", "Cabin_type"], axis=0)

src/utils.py

@@ -1,8 +1,12 @@
-from typing import Tuple
+import math
+from typing import Dict, Tuple
 
+import numpy as np
 import pandas as pd
 from pandas import DataFrame
+from sklearn import metrics
 from sklearn.model_selection import train_test_split
+from sklearn.pipeline import Pipeline
 
 
 def split_stratified_into_train_val_test(
@@ -77,3 +81,58 @@ def split_stratified_into_train_val_test(
 
     assert len(df_input) == len(df_train) + len(df_val) + len(df_test)
     return df_train, df_val, df_test, y_train, y_val, y_test
+
+
+def run_classification(
+    model: Pipeline,
+    X_train: DataFrame,
+    X_test: DataFrame,
+    y_train: DataFrame,
+    y_test: DataFrame,
+) -> Dict:
+    result = {}
+    y_train_predict = model.predict(X_train)
+    y_test_probs = model.predict_proba(X_test)[:, 1]
+    y_test_predict = np.where(y_test_probs > 0.5, 1, 0)
+
+    result["pipeline"] = model
+    result["probs"] = y_test_probs
+    result["preds"] = y_test_predict
+
+    result["Precision_train"] = metrics.precision_score(y_train, y_train_predict)
+    result["Precision_test"] = metrics.precision_score(y_test, y_test_predict)
+    result["Recall_train"] = metrics.recall_score(y_train, y_train_predict)
+    result["Recall_test"] = metrics.recall_score(y_test, y_test_predict)
+    result["Accuracy_train"] = metrics.accuracy_score(y_train, y_train_predict)
+    result["Accuracy_test"] = metrics.accuracy_score(y_test, y_test_predict)
+    result["ROC_AUC_test"] = metrics.roc_auc_score(y_test, y_test_probs)
+    result["F1_train"] = metrics.f1_score(y_train, y_train_predict)
+    result["F1_test"] = metrics.f1_score(y_test, y_test_predict)
+    result["MCC_test"] = metrics.matthews_corrcoef(y_test, y_test_predict)
+    result["Cohen_kappa_test"] = metrics.cohen_kappa_score(y_test, y_test_predict)
+    result["Confusion_matrix"] = metrics.confusion_matrix(y_test, y_test_predict)
+
+    return result
+
+
+def run_regression(
+    model: Pipeline,
+    X_train: DataFrame,
+    X_test: DataFrame,
+    y_train: DataFrame,
+    y_test: DataFrame,
+) -> Dict:
+    result = {}
+    y_train_pred = model.predict(X_train.values)
+    y_test_pred = model.predict(X_test.values)
+
+    result["fitted"] = model
+    result["train_preds"] = y_train_pred
+    result["preds"] = y_test_pred
+
+    result["RMSE_train"] = math.sqrt(metrics.mean_squared_error(y_train, y_train_pred))
+    result["RMSE_test"] = math.sqrt(metrics.mean_squared_error(y_test, y_test_pred))
+    result["RMAE_test"] = math.sqrt(metrics.mean_absolute_error(y_test, y_test_pred))
+    result["R2_test"] = metrics.r2_score(y_test, y_test_pred)
+
+    return result