ud120-projects/final_project/tester.py

#!/usr/bin/pickle

""" a basic script for importing student's POI identifier,
    and checking the results that they get from it 
 
    requires that the algorithm, dataset, and features list
    be written to my_classifier.pkl, my_dataset.pkl, and
    my_feature_list.pkl, respectively

    that process should happen at the end of poi_id.py
"""

import pickle
import sys
from sklearn.model_selection import StratifiedShuffleSplit
import os

sys.path.append(os.path.abspath(("../tools/")))
from feature_format import featureFormat, targetFeatureSplit

PERF_FORMAT_STRING = "\
\tAccuracy: {:>0.{display_precision}f}\tPrecision: {:>0.{display_precision}f}\t\
Recall: {:>0.{display_precision}f}\tF1: {:>0.{display_precision}f}\tF2: {:>0.{display_precision}f}"
RESULTS_FORMAT_STRING = "\tTotal predictions: {:4d}\tTrue positives: {:4d}\tFalse positives: {:4d}\
\tFalse negatives: {:4d}\tTrue negatives: {:4d}"

def test_classifier(clf, dataset, feature_list, folds = 1000):
    data = featureFormat(dataset, feature_list, sort_keys = True)
    labels, features = targetFeatureSplit(data)
    cv = StratifiedShuffleSplit(folds, random_state = 42)
    true_negatives = 0
    false_negatives = 0
    true_positives = 0
    false_positives = 0
    for train_idx, test_idx in cv.split(features, labels): 
        features_train = []
        features_test  = []
        labels_train   = []
        labels_test    = []
        for ii in train_idx:
            features_train.append( features[ii] )
            labels_train.append( labels[ii] )
        for jj in test_idx:
            features_test.append( features[jj] )
            labels_test.append( labels[jj] )
        
        ### fit the classifier using training set, and test on test set
        clf.fit(features_train, labels_train)
        predictions = clf.predict(features_test)
        for prediction, truth in zip(predictions, labels_test):
            if prediction == 0 and truth == 0:
                true_negatives += 1
            elif prediction == 0 and truth == 1:
                false_negatives += 1
            elif prediction == 1 and truth == 0:
                false_positives += 1
            elif prediction == 1 and truth == 1:
                true_positives += 1
            else:
                print("Warning: Found a predicted label not == 0 or 1.")
                print("All predictions should take value 0 or 1.")
                print("Evaluating performance for processed predictions:")
                break
    try:
        total_predictions = true_negatives + false_negatives + false_positives + true_positives
        accuracy = 1.0*(true_positives + true_negatives)/total_predictions
        precision = 1.0*true_positives/(true_positives+false_positives)
        recall = 1.0*true_positives/(true_positives+false_negatives)
        f1 = 2.0 * true_positives/(2*true_positives + false_positives+false_negatives)
        f2 = float()
        if precision == 0 and recall == 0:
            f2 = 0
        else:
            f2 = (1+2.0*2.0) * precision*recall/(4*precision + recall)
        print(clf)
        print(PERF_FORMAT_STRING.format(accuracy, precision, recall, f1, f2, display_precision = 5))
        print(RESULTS_FORMAT_STRING.format(total_predictions, true_positives, false_positives, false_negatives, true_negatives))
        print("")
    except ZeroDivisionError:
        print("Got a divide by zero when trying out:", clf)
        print("Precision or recall may be undefined due to a lack of true positive predicitons.")

CLF_PICKLE_FILENAME = "my_classifier.pkl"
DATASET_PICKLE_FILENAME = "my_dataset.pkl"
FEATURE_LIST_FILENAME = "my_feature_list.pkl"

def dump_classifier_and_data(clf, dataset, feature_list):
    with open(CLF_PICKLE_FILENAME, "wb") as clf_outfile:
        pickle.dump(clf, clf_outfile)
    with open(DATASET_PICKLE_FILENAME, "wb") as dataset_outfile:
        pickle.dump(dataset, dataset_outfile)
    with open(FEATURE_LIST_FILENAME, "wb") as featurelist_outfile:
        pickle.dump(feature_list, featurelist_outfile)

def load_classifier_and_data():
    with open(CLF_PICKLE_FILENAME, "rb") as clf_infile:
        clf = pickle.load(clf_infile)
    with open(DATASET_PICKLE_FILENAME, "rb") as dataset_infile:
        dataset = pickle.load(dataset_infile)
    with open(FEATURE_LIST_FILENAME, "rb") as featurelist_infile:
        feature_list = pickle.load(featurelist_infile)
    return clf, dataset, feature_list

def main():
    ### load up student's classifier, dataset, and feature_list
    clf, dataset, feature_list = load_classifier_and_data()
    ### Run testing script
    test_classifier(clf, dataset, feature_list)

if __name__ == '__main__':
    main()