TensorFlow

TensorFlow

TensorFlow

tensorflow_basics_01.py

################################################################################################
#	name:	tensorflow_basics_01.py
#	desc:	Gettig started with tensorflow with simple multiplication
#	date:	2019-01-19
#	Author:	conquistadorjd
################################################################################################
import tensorflow as tf

print("*** Program Started ***")
# Initialize two constants
x1 = tf.constant(2)
x2 = tf.constant(7)

# Multiply
result = tf.multiply(x1, x2)

# Print the result
print(result)

# Intialize the Session
sess = tf.Session()
# Print the result
print(sess.run(result))
# Close the session
sess.close()

print("*** Program Ended ***")

tensorflow_basics_02.py

################################################################################################
#	name:	tensorflow_basics_02.py
#	desc:	Gettig started with tensorflow with simple multiplication of matrices
#	date:	2019-01-19
#	Author:	conquistadorjd
################################################################################################
import tensorflow as tf

print("*** Program Started ***")
# Initialize two constants
x1 = tf.constant([1,2,3,4])
x2 = tf.constant([5,6,7,8])

# Multiply
result = tf.multiply(x1, x2)

# Print the result
print(result)

with tf.Session() as sess:
  output = sess.run(result)
  print(output)

print("*** Program Ended ***")

tensorflow_regression_linear_01.py

################################################################################################
#	name:	tensorflow_regression_linear_01.py
#	desc:	Gettig started with tensorflow with linear regression
#	date:	2019-01-19
#	Author:	conquistadorjd
################################################################################################

import numpy as np
import seaborn
from matplotlib import pyplot as plt
import tensorflow as tf

from sklearn import datasets, linear_model
from sklearn.metrics import mean_squared_error, r2_score

print("*** Program Started ***")

######################################################################################## input data
##### Input Data #1
# y_data=[1,3,5,3,8,12]
# x_data=[1,2,3,4,5,6]
##### Input Data #2
# x_data = np.arange(100, step=20)
# y_data = x_data + 20 * np.sin(x_data/10)
##### Input Data #3
# x_data = [1, 2, 3, 4]
# y_data = [2, 4, 6, 8]
##### Input Data #4
x_data = [6, 9, 12, 15,20,25,31,37,44,54]
y_data = [10,15, 14, 18,25,35,50,65,80,95]

######################################################################################## regression using sklearn
####  change specific to sklearn
x = np.array(x_data).reshape(-1, 1)
y = y_data
# print(len(x_data), len(y_data))
regr = linear_model.LinearRegression()
regr.fit(x, y)

m=regr.coef_[0]
b=regr.intercept_
print("****Using sklearn \n slope=",m, "\nintercept=",b,"\n***")

# xx= x
# yy = regr.predict(xx)
# plt.scatter(x,y,s=None, marker='o',color='g',edgecolors='g',alpha=0.9,label="Jagur")
# plt.plot(xx,yy)
# plt.show()

######################################################################################## regression using TensorFlow
# Define input data
# variable for parameter slope (W)
W = tf.Variable([1.0], tf.float32)
 
#variable for parameter bias (b)
b = tf.Variable([1.0], tf.float32)
 
# placeholders for independent variable, denoted by x
x = tf.placeholder(tf.float32)
 
# Equation of Linear Regression
linear_model = W * x + b
 
# Initializing the session
sess = tf.Session()

init = tf.global_variables_initializer()
sess.run(init)
 
# running regression model 
print(sess.run(linear_model, {x: x_data})) 

# placefolder for dependent variable
y = tf.placeholder(tf.float32)

#Loss function
loss = tf.reduce_sum(tf.square(linear_model - y))
print(sess.run(loss, {x:x_data, y:y_data}))

# an instance of gradient descent optimizer
optimizer = tf.train.GradientDescentOptimizer(0.01)
 
train = optimizer.minimize(loss)
 
for i in range(1000):
     sess.run(train, {x:x_data, y:y_data})
print("*** Using TensorFlow")
print(sess.run([W, b]))

print("*** Program Ended ***")