-
Notifications
You must be signed in to change notification settings - Fork 0
/
NFLX.py
201 lines (184 loc) · 6.59 KB
/
NFLX.py
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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
import numpy
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from pandas import read_csv
import math
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
netflix = pd.read_csv('NFLX.csv')
print(netflix.shape)
print(netflix.head())
# netflix=netflix[['Close']]
# print(netflix.head())
#
# # fix random seed for reproducibility
# np.random.seed(7)
# netflix = netflix.values
# netflix = netflix.astype('float32')
#
# # normalize the dataset
# scaler = MinMaxScaler(feature_range=(0, 1))
# netflix = scaler.fit_transform(netflix)
#
# # split into train and test sets
# train_size = int(len(netflix) * 0.70)
# test_size = len(netflix) - train_size
# train, test = netflix[0:train_size,:], \
# netflix[train_size:len(netflix),:]
# print(len(train), len(test))
#
# #create look back function
# def create_netflix(netflix, look_back=1):
# # convert an array of values into a dataset matrix
# dataX, dataY = [], []
# for i in range(len(netflix)-look_back-1):
# a = netflix[i:(i+look_back), 0]
# dataX.append(a)
# dataY.append(netflix[i + look_back, 0])
# return numpy.array(dataX), numpy.array(dataY)
# # fix random seed for reproducibility
# numpy.random.seed(7)
#
# # reshape into X=t and Y=t+1
# look_back = 1
# trainX, trainY = create_netflix(train, look_back)
# testX, testY = create_netflix(test, look_back)
#
# # reshape input to be [samples, time steps, features]
# trainX = numpy.reshape(trainX, (trainX.shape[0], 1,
# trainX.shape[1]))
# testX = numpy.reshape(testX, (testX.shape[0], 1, testX.shape[1]))
#
# # create and fit the LSTM network
# model = Sequential()
# model.add(LSTM(5, input_shape=(1, look_back)))
# model.add(Dense(1))
# model.compile(loss='mean_squared_error', optimizer='adam')
# model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)
#
# #predicting and inverse transforming the predictions
# # make predictions
# trainPredict = model.predict(trainX)
# testPredict = model.predict(testX)
# #invert predictions
# trainPredict = scaler.inverse_transform(trainPredict)
# trainY = scaler.inverse_transform([trainY])
# testPredict = scaler.inverse_transform(testPredict)
# testY = scaler.inverse_transform([testY])
# # calculate root mean squared error
# trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
# print('Train Score: %.2f RMSE' % (trainScore))
# testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
# print('Test Score: %.2f RMSE' % (testScore))
#
# # shift train predictions for plotting
# trainPredictPlot = numpy.empty_like(netflix)
# trainPredictPlot[:, :] = numpy.nan
# trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict
#
# # shift test predictions for plotting
# testPredictPlot = numpy.empty_like(netflix)
# testPredictPlot[:, :] = numpy.nan
# testPredictPlot[len(trainPredict)+(look_back*2)+1:len(netflix)-1, :] = testPredict
#
# # plot baseline and predictions
# plt.plot(scaler.inverse_transform(netflix))
# plt.plot(trainPredictPlot)
# plt.plot(testPredictPlot)
# plt.show()
# #
# #comparison of actual and predicted
# actual = np.append(trainY, testY)
# predicted = np.append(trainPredict, testPredict)
# result_df =pd.DataFrame()
# result_df['Actual_Y']= actual
# result_df['Predicted_Y']=predicted
# print(result_df.head())
#
#
#Filter data for period 21-04-2021 - 21-04-2022
netflix_x = netflix.loc[(netflix['Date'] >= '2021-04-01') & (netflix['Date'] < '2022-04-22')]
#print(netflix_x.head())
#netflix_x.to_csv('prev_data.csv', index=False)
netflix = pd.read_csv('prev_data.csv')
print(netflix.head())
netflix=netflix[['Close']]
print(netflix.head())
# fix random seed for reproducibility
np.random.seed(7)
netflix = netflix.values
netflix = netflix.astype('float32')
# normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
netflix = scaler.fit_transform(netflix)
# split into train and test sets
train_size = int(len(netflix) * 0.70)
test_size = len(netflix) - train_size
train, test = netflix[0:train_size,:], \
netflix[train_size:len(netflix),:]
print(len(train), len(test))
#create look back function
def create_netflix(netflix, look_back=1):
# convert an array of values into a dataset matrix
dataX, dataY = [], []
for i in range(len(netflix)-look_back-1):
a = netflix[i:(i+look_back), 0]
dataX.append(a)
dataY.append(netflix[i + look_back, 0])
return numpy.array(dataX), numpy.array(dataY)
# fix random seed for reproducibility
numpy.random.seed(7)
# reshape into X=t and Y=t+1
look_back = 1
trainX, trainY = create_netflix(train, look_back)
testX, testY = create_netflix(test, look_back)
# reshape input to be [samples, time steps, features]
trainX = numpy.reshape(trainX, (trainX.shape[0], 1,
trainX.shape[1]))
testX = numpy.reshape(testX, (testX.shape[0], 1, testX.shape[1]))
# create and fit the LSTM network
model = Sequential()
model.add(LSTM(5, input_shape=(1, look_back)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)
#predicting and inverse transforming the predictions
# make predictions
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)
#invert predictions
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])
# calculate root mean squared error
trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
print('Test Score: %.2f RMSE' % (testScore))
# shift train predictions for plotting
trainPredictPlot = numpy.empty_like(netflix)
trainPredictPlot[:, :] = numpy.nan
trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict
# shift test predictions for plotting
testPredictPlot = numpy.empty_like(netflix)
testPredictPlot[:, :] = numpy.nan
testPredictPlot[len(trainPredict)+(look_back*2)+1:len(netflix)-1, :] = testPredict
# plot baseline and predictions
plt.title('Predicted vs Actual for 12 months')
plt.plot(scaler.inverse_transform(netflix))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.show()
#
#comparison of actual and predicted
actual = np.append(trainY, testY)
predicted = np.append(trainPredict, testPredict)
result_df =pd.DataFrame()
result_df['Actual_Y']= actual
result_df['Predicted_Y']=predicted
print(result_df.head())