Logistic regression script

from __future__ import print_function

import tensorflow as tf
import numpy
import matplotlib.pyplot as plt
import pandas as pd
import os
os.chdir('/Users/Nick/Git/Machinelearning')

# Define our dataset
dataset = pd.read_csv('first1500.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 3].values

#Fill in the gaps of the data
from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values = 0, strategy = 'mean')
imputer = imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])

#Categorize city names
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()

#Split the dataset into our train and test sets
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)

# Set our learning rate and training epoch
learningrate = 0.01
trainingepochs = 100
display_step = 50

# Generate a random number
rng = numpy.random

# tf Graph Input
X = tf.placeholder("float")
Y = tf.placeholder("float")

# Set model weights
W = tf.Variable(rng.randn(), name="weight")
b = tf.Variable(rng.randn(), name="bias")

# Construct a linear model
pred = tf.add(tf.mul(X, W), b)

# Mean squared error
n_samples = X_train.shape[0]
cost = tf.reduce_sum(tf.pow(pred-Y, 2))/(2*n_samples)
#cost = (tf.square(y-y_train))
# Gradient descent
optimizer = tf.train.GradientDescentOptimizer(learningrate).minimize(cost)

# Initializing the variables
init = tf.global_variables_initializer()

# Launch the graph
with tf.Session() as sess:
    sess.run(init)

    # Fit all training data
    for epoch in range(trainingepochs):
        for (x, y) in zip(X_train, y_train):
            sess.run(optimizer, feed_dict={X: x, Y: y})

        # Display logs per epoch step
        if (epoch+1) % display_step == 0:
            c = sess.run(cost, feed_dict={X: X_train, Y: y_train})
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c), \
                "W=", sess.run(W), "b=", sess.run(b))

    print("Optimization Finished!")
    training_cost = sess.run(cost, feed_dict={X: X_train, Y: y_train})
    print("Training cost=", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n')

    # Graphic display
    plt.plot(X_train, y_train, 'ro', label='Original data')
    plt.plot(X_train, sess.run(W) * X_train + sess.run(b), label='Fitted line')
    plt.legend()
    plt.show()

    print("Testing... (Mean square loss Comparison)")
    testing_cost = sess.run(
        tf.reduce_sum(tf.pow(pred - Y, 2)) / (2 * X_test.shape[0]),
        feed_dict={X: X_test, Y: y_test})  # same function as cost above
    print("Testing cost=", testing_cost)
    print("Absolute mean square loss difference:", abs(
        training_cost - testing_cost))

    plt.plot(X_test, y_test, 'bo', label='Testing data')
    plt.plot(X_train, sess.run(W) * X_train + sess.run(b), label='Fitted line')
    plt.legend()
    plt.show()