-
Notifications
You must be signed in to change notification settings - Fork 2
/
time_series_ridge_regression.py
147 lines (122 loc) · 5.21 KB
/
time_series_ridge_regression.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
import numpy as np
import pandas as pd
import datetime
import matplotlib.pyplot as plt
from sklearn.cross_validation import train_test_split
import sklearn.preprocessing as preprocessing
from sklearn import linear_model
from sklearn.metrics import mean_squared_error
from sklearn import ensemble
import csv
import write_submission
import read_dataset
def split_and_build_class(X, y):
X_train = X[: 4061]
X_test = X[4061:]
y_train = y[: 4061]
y_test = y[4061:]
print X_train.shape
print X_test.shape
# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
# Normalize the input data.
imp = preprocessing.Imputer(missing_values='NaN', strategy='mean', axis=0)
fixed_X_train = X_train[:, 1:]
imp.fit(fixed_X_train)
fixed_X_train = imp.transform(fixed_X_train)
# preprocessing.normalize(fixed_X_train, copy=False)
X_train[:, 1:] = fixed_X_train
fixed_X_test = X_test[:, 1:]
imp.fit(fixed_X_test)
fixed_X_test = imp.transform(fixed_X_test)
# preprocessing.normalize(fixed_X_test, copy=False)
X_test[:, 1:] = fixed_X_test
train_data = read_dataset.microData()
train_data.get_data(X_train)
y_train = train_data.set_output(y_train)
test_data = read_dataset.microData()
test_data.get_data(X_test)
y_test = test_data.set_output(y_test)
return [X_train, X_test, y_train, y_test, train_data, test_data]
def run_regression(X, y):
clf = linear_model.Ridge(normalize=True)
# clf = ensemble.BaggingRegressor(n_estimators=1000)
clf.fit(X, y)
return clf
def main():
# Read the dataset.
dataset_path = './dataset/'
dataset_file_path = './dataset_file_path.csv'
df_path = pd.read_csv(dataset_file_path)
all_file_param = read_dataset.read_all_dataset(df_path)
file_amount = len(all_file_param)
plot_files = ['Training set Microclimate (2 hour intervals)']
yield_file = 'Target Variable Water Yield'
# plot_files = ['Training set Microclimate (2 hour intervals)',
# 'Training set Microclimate (5 minute intervals)']
# Set up features for micro files.
micro_features = read_dataset.set_features(dataset_path, plot_files)
# Read yield file for micro training file.
yield_df = None
for k in xrange(file_amount):
file = all_file_param[k]
if file.data_name == yield_file:
yield_path = dataset_path + file.file_path
yield_df = pd.read_csv(yield_path)
break
# Traverse all the dataset.
for k in xrange(file_amount):
file = all_file_param[k]
if file.data_name not in plot_files:
continue
print '==========' + file.data_name + '=========='
path = dataset_path + file.file_path
df = pd.read_csv(path)
# Split the micro training file into training dataset and test dataset.
X_train, X_test, y_train, y_test, train_data, test_data = split_and_build_class(df.values, yield_df.values)
# [train_data, test_data] = split_and_build_class(df.values, yield_df.values)
# Run Ridge Regression.
clf = run_regression(X_train[:, 1:], y_train)
y_hat_test = clf.predict(X_test[:, 1:])
cmap = plt.get_cmap('jet_r')
plt.figure(figsize=(10, 10))
interval = file.interval
intervel_minute = read_dataset.get_interval_minute(interval)
test_size = y_hat_test.shape[0]
plt.plot([i for i in xrange(test_size)], y_hat_test)
plt.plot([i for i in xrange(test_size)], y_test)
plt.legend(['Prediction', 'Real'])
plt.suptitle('Time Series + Ridge Regression')
plt.savefig('Time Series + Ridge Regression.png', bbox_inches='tight')
loss = np.sqrt(mean_squared_error(y_test, y_hat_test))
print 'Time Series + Ridge Regression loss =', loss
'''
=======================================================================
'''
# Predict test and write submission
submission_file_name = 'Submission format'
submission_file = None
test_file_name = 'Test set Microclimate (2 hour intervals)'
test_file = None
for k in xrange(file_amount):
file = all_file_param[k]
if file.data_name == submission_file_name:
submission_file = file
break
submission_path = dataset_path + submission_file.file_path
df_submission = pd.read_csv(submission_path, index_col=0, parse_dates=[0])
for k in xrange(file_amount):
file = all_file_param[k]
if file.data_name == test_file_name:
test_file = file
break
test_path = dataset_path + test_file.file_path
df_test = pd.read_csv(test_path, index_col=0, parse_dates=[0])
X_combined = write_submission.combine_table(df_submission, df_test)
imp = preprocessing.Imputer(missing_values='NaN', strategy='mean', axis=0)
fixed_X = X_combined.values[:, 0:]
imp.fit(fixed_X)
X_combined.values[:, 0:] = imp.transform(fixed_X)
# preprocessing.normalize(fixed_X, copy=False)
y_submission = write_submission.write_submission(
X_combined, clf, df_submission, 'Time Series + Ridge Regression Submission')
main()