from sklearn.metrics import accuracy_score, precision_score, recall_score
from time import time

val_features_raw = pd.read_csv('val_features_raw.csv')
val_features_reduced = pd.read_csv('val_features_reduced.csv')
val_features_transformed = pd.read_csv('val_features_transformed.csv')


val_labels = pd.read_csv('val_labels.csv')

# Read in models
models = {}

for mdl in ['raw_original', 'raw_reduced', 'raw_transformed']:
    models[mdl] = joblib.load('mdl_{}_features.pkl'.format(mdl))
    
def evaluate_model(name, model, features, labels):
    start = time()
    pred = model.predict(features)
    end = time()
    accuracy = round(accuracy_score(labels, pred), 3)
    precision = round(precision_score(labels, pred), 3)
    recall = round(recall_score(labels, pred), 3)
    print('{} -- \tAccuracy: {} / Precision: {} / Recall: {} / Latency: {}ms'.format(name,
                                                                                     accuracy,
                                                                                     precision,
                                                                                     recall,
                                                                                     round((end - start)*1000, 1)))
# Evaluate all of our models on the validation set
evaluate_model('Raw Features', models['raw_original'], val_features_raw, val_labels)
evaluate_model('reduced Features', models['raw_reduced'], val_features_reduced, val_labels)
evaluate_model('Transformed Features', models['raw_transformed'], val_features_transformed, val_labels)