python-tensorflow-google/first_steps_with_tensor_flow.py at master · AntonioErdeljac/python-tensorflow-google · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
#!/usr/bin/env python
# coding: utf-8

# In[15]:


from __future__ import print_function

import math

from IPython import display
from matplotlib import cm
from matplotlib import gridspec
from matplotlib import pyplot as plt
import numpy as np
import pandas as pd
from sklearn import metrics
import tensorflow as tf
from tensorflow.python.data import Dataset

tf.logging.set_verbosity(tf.logging.ERROR)
pd.options.display.max_rows = 10
pd.options.display.float_format = '{:.1f}'.format


# In[16]:


california_housing_dataframe = pd.read_csv("https://download.mlcc.google.com/mledu-datasets/california_housing_train.csv", sep=",")


# In[17]:


california_housing_dataframe = california_housing_dataframe.reindex(
    np.random.permutation(california_housing_dataframe.index)
)
california_housing_dataframe["median_house_value"] /= 1000.0
california_housing_dataframe


# In[18]:


california_housing_dataframe.describe()


# In[19]:


my_feature = california_housing_dataframe[["total_rooms"]]

feature_columns = [tf.feature_column.numeric_column("total_rooms")]


# In[20]:


targets = california_housing_dataframe["median_house_value"]


# In[21]:


my_optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.0000001)
my_optimizer = tf.contrib.estimator.clip_gradients_by_norm(my_optimizer, 5.0)

linear_regressor = tf.estimator.LinearRegressor(
    feature_columns = feature_columns,
    optimizer = my_optimizer
)


# In[22]:


def my_input_fn(features, targets, batch_size=1, shuffle=True, num_epochs=None):
    features = {key: np.array(value) for key, value in dict(features).items()}

    ds = Dataset.from_tensor_slices((features, targets))
    ds = ds.batch(batch_size).repeat(num_epochs)

    if shuffle:
        ds = ds.shuffle(buffer_size=10000)

    features, labels = ds.make_one_shot_iterator().get_next()
    return features, labels


# In[23]:


_ = linear_regressor.train(
    input_fn = lambda:my_input_fn(my_feature, targets),
    steps=100
)


# In[24]:


prediction_input_fn = lambda: my_input_fn(my_feature, targets, num_epochs = 1, shuffle = False)

predictions = linear_regressor.predict(input_fn = prediction_input_fn)

predictions = np.array([item['predictions'][0] for item in predictions])

mean_squared_error = metrics.mean_squared_error(predictions, targets)
root_mean_squared_error = math.sqrt(mean_squared_error)

print("MSE (training data): %0.3f" % mean_squared_error)
print("RMSE (training data): %0.3f" % root_mean_squared_error)


# In[26]:


min_house_value = california_housing_dataframe["median_house_value"].min()
max_house_value = california_housing_dataframe["median_house_value"].max()
min_max_difference = max_house_value - min_house_value

print("Min. median house value: %0.3f" % min_house_value)
print("Max. median house value: %0.3f" % max_house_value)
print("Difference between min. and max.: %0.3f" % min_max_difference)
print("RMSE: %0.3f" % root_mean_squared_error)


# In[27]:


calibration_data = pd.DataFrame()
calibration_data["predictions"] = pd.Series(predictions)
calibration_data["targets"] = pd.Series(targets)
calibration_data.describe()


# In[28]:


sample = california_housing_dataframe.sample(n=300)


# In[31]:


x_0 = sample["total_rooms"].min()
x_1 = sample["total_rooms"].max()

weight = linear_regressor.get_variable_value('linear/linear_model/total_rooms/weights')[0]
bias = linear_regressor.get_variable_value('linear/linear_model/bias_weights')

y_0 = weight * x_0 + bias
y_1 = weight * x_1 + bias

plt.plot([x_0, x_1], [y_0, y_1], c = 'r')

plt.ylabel("median_house_value")
plt.xlabel("total_rooms")

plt.scatter(sample["total_rooms"], sample["median_house_value"])

plt.show()


# In[ ]: