Task 1: Logistic Regression Assignment

Scaffold Head

import numpy as np import csv def get_titanic(split_ratio=0.66, seed=42, affine_embedding=False): X, Y = [], [] # parse the data, omit the name with open('titanic.csv', 'r') as csvfile: reader = csv.reader(csvfile, delimiter=',') for row in reader: try: label = row[0] feats = row[1:2]+[row[3] == "female"]+row[4:] if affine_embedding: feats += [1] X.append([float(x) for x in feats]) Y.append([float(y) for y in label]) except: print("# Skipped row:", row) X, Y = np.array(X), np.array(Y) # split the data according to train/test ratio np.random.seed(seed) iota = np.random.choice(len(X), len(X), replace=False) offs = int(split_ratio*len(X)) return (X[iota[:offs]], Y[iota[:offs]]), \ (X[iota[offs:]], Y[iota[offs:]]) def sigmoid(z): return 1.0/(1.0+np.exp(-z)) def forward_evaluate(X, B): return sigmoid(X.dot(B)) def loss_and_accuracy(X, Y, B): F = forward_evaluate(X, B) return -np.mean(Y*np.log(F)+(1-Y)*np.log(1-F)), \ np.mean(np.round(F) == Y)

Scaffold Foot

loss, acc = loss_and_accuracy(X_test, Y_test, B) print("Deep Learning is fun!" if acc > 0.70 else "Deep Learning sucks!")

Start time:

Mo 22 Okt 2018 10:51:00

End time:

Mi 14 Nov 2018 12:00:00

General test timeout:

10.0 seconds

Tests

Deep Learning is fun!