Show model performance directly from predict_data

src/processing.py

@@ -1,5 +1,5 @@
 from numpy import mean
-from sklearn.metrics import classification_report, confusion_matrix
+from sklearn.metrics import confusion_matrix, accuracy_score
 from sklearn.model_selection import cross_val_score
 from sklearn.naive_bayes import GaussianNB
 from sklearn.neighbors import KNeighborsClassifier
@@ -25,31 +25,31 @@ def predict_data(data, target, model):
     model = choose_model(model)
     if model == "knn":
         data = scale(data)
-    predictions = []
+    accuracy_scores = []
+    confusion_matrices = []
     for train_index, test_index in split_k_sets(data):
         model.fit(data.iloc[train_index], target.iloc[train_index])
         prediction = model.predict(data.iloc[test_index])
-        predictions.append(prediction)
+        accuracy_scores.append(accuracy_score(target.iloc[test_index], prediction))
-    return model, predictions
+        confusion_matrices.append(confusion_matrix(target.iloc[test_index], prediction))
+    cv_score = cross_val_score(model, data, target, cv=10)
+    evaluate_performance(
+        confusion_matrix=mean(confusion_matrices, axis=0),
+        accuracy=mean(accuracy_scores),
+        cv_score=mean(cv_score),
+    )
 
 
-def evaluate_performance(predictions, model, data, target):
+def evaluate_performance(confusion_matrix, accuracy, cv_score):
-    confusion_matrices = []
+    print("Accuracy Score: " + str(accuracy))
-    classification_reports = []
+    print("Confusion matrix: ")
-    score = cross_val_score(model, data, target, cv=10)
+    print(str(confusion_matrix))
-    for prediction in predictions:
+    print("Cross validation score: " + str(cv_score))
-        confusion_matrices.append(confusion_matrix(target, prediction))
-        classification_reports.append(classification_report(target, prediction))
-    print("Model:" + model)
-    print("Score: " + score)
-    print("Confusion matrix: " + mean(confusion_matrices))
-    print("Classification report: " + mean(classification_reports))
 
 
 def main():
-    data, target = parse_data(source="../data/mamografia.csv", action="fill")
+    data, target = parse_data(source="data/mamografia.csv", action="drop")
-    model, predictions = predict_data(data=data, target=target, model="knn")
+    predict_data(data=data, target=target, model="svc")
-    evaluate_performance(predictions=predictions, model=model, data=data, target=target)
 
 
 if __name__ == "__main__":