model_perf

model_test.py

#Prediction from test dataset
from sklearn.metrics import classification_report, confusion_matrix, f1_score, precision_score, recall_score
model_name=[]
precision_array=[]
recall_array=[]
f1_array=[]
test_time=[]
print("Classifiation Report\n")
print("*****************************************************")
for i, pipeline in enumerate(pipelines):
    start=time.time()
    y_pred=pipeline.predict(X_test)
    stop=time.time()
    test_time.append(stop-start)
    print(pipelines[i].steps[1][0].upper())
    model_name.append(pipelines[i].steps[1][0].upper())
    f1_array.append(round(f1_score(y_test, y_pred, average='weighted'),2))
    precision_array.append(round(precision_score(y_test, y_pred, average='binary'),2))
    recall_array.append(round(recall_score(y_test, y_pred, average='binary'),2))
    print("\n",classification_report(y_test, y_pred))
    print("*****************************************************")