In [11]:

    

from __future__ import division
import tensorflow as tf
import numpy as np
import tarfile
import os
import matplotlib.pyplot as plt
import time

# Display plots inline 
%matplotlib inline


    

In [12]:

    

### IMPORT DATA ###


def csv_to_numpy_array(filePath, delimiter):
    return np.genfromtxt(filePath, delimiter=delimiter, dtype=None)

def import_data():
    if "data" not in os.listdir(os.getcwd()):
        # Untar directory of data if we haven't already
        tarObject = tarfile.open("tensorflow-tutorial/data.tar.gz")
        tarObject.extractall()
        tarObject.close()
        print("Extracted tar to current directory")
    else:
        # we've already extracted the files
        pass

    print("loading training data")
    trainX = csv_to_numpy_array("data/trainX.csv", delimiter="\t")
    trainY = csv_to_numpy_array("data/trainY.csv", delimiter="\t")
    print("loading test data")
    testX = csv_to_numpy_array("data/testX.csv", delimiter="\t")
    testY = csv_to_numpy_array("data/testY.csv", delimiter="\t")
    return trainX,trainY,testX,testY

trainX,trainY,testX,testY = import_data()


    

    




loading training data
loading test data

In [13]:

    

numFeatures = trainX.shape[1]
# numLabels = number of classes we are predicting (here just 2: Ham or Spam)
numLabels = trainY.shape[1]

# TRAINING SESSION PARAMETERS
# number of times we iterate through training data
# tensorboard shows that accuracy plateaus at ~25k epochs
numEpochs = 27000
# a smarter learning rate for gradientOptimizer
learningRate = tf.train.exponential_decay(learning_rate=0.0008,
                                          global_step= 1,
                                          decay_steps=trainX.shape[0],
                                          decay_rate= 0.95,
                                          staircase=True)


    

In [14]:

    

X = tf.placeholder(tf.float32, [None, numFeatures])
# yGold = Y-matrix / label-matrix / labels... This will be our correct answers
# matrix. Every row has either [1,0] for SPAM or [0,1] for HAM. 'None' here 
# means that we can hold any number of emails
yGold = tf.placeholder(tf.float32, [None, numLabels])

weights = tf.Variable(tf.random_normal([numFeatures,numLabels],
                                       mean=0,
                                       stddev=(np.sqrt(6/numFeatures+
                                                         numLabels+1)),
                                       name="weights"))

bias = tf.Variable(tf.random_normal([1,numLabels],
                                    mean=0,
                                    stddev=(np.sqrt(6/numFeatures+numLabels+1)),
                                    name="bias"))


    

In [15]:

    

#PREDICTION OPS #INITIALIZE our weights and biases


init_OP = tf.initialize_all_variables()

# PREDICTION ALGORITHM i.e. FEEDFORWARD ALGORITHM
apply_weights_OP = tf.matmul(X, weights, name="apply_weights")
add_bias_OP = tf.add(apply_weights_OP, bias, name="add_bias") 
activation_OP = tf.nn.sigmoid(add_bias_OP, name="activation")

### EVALUATION OP ###


# COST FUNCTION i.e. MEAN SQUARED ERROR
cost_OP = tf.nn.l2_loss(activation_OP-yGold, name="squared_error_cost")


### OPTIMIZATION OP ###


# OPTIMIZATION ALGORITHM i.e. GRADIENT DESCENT
training_OP = tf.train.GradientDescentOptimizer(learningRate).minimize(cost_OP)


    

In [10]:

    

### GRAPH LIVE UPDATING ###


epoch_values=[]
accuracy_values=[]
cost_values=[]
# Turn on interactive plotting
plt.ion()
# Create the main, super plot
fig = plt.figure()
# Create two subplots on their own axes and give titles
ax1 = plt.subplot("211")
ax1.set_title("TRAINING ACCURACY", fontsize=18)
ax2 = plt.subplot("212")
ax2.set_title("TRAINING COST", fontsize=18)
plt.tight_layout()


    

In [ ]: