-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathquantclean.py
191 lines (142 loc) · 6.2 KB
/
quantclean.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
import pandas as pd
from pandas_datareader import data as web
import logging
def sweeper(data):
for name in logging.Logger.manager.loggerDict.keys():
logging.getLogger(name).setLevel(logging.CRITICAL)
#non efficient, right?
data.columns = ['Open' if 'open' in x else 'Open' if 'OPEN' in x else x for x in data.columns]
data.columns = ['High' if 'high' in x else 'High' if 'HIGH' in x else x for x in data.columns]
data.columns = ['Low' if 'low' in x else 'Low' if 'LOW' in x else x for x in data.columns]
data.columns = ['Close' if 'close' in x else 'Close' if 'CLOSE' in x else x for x in data.columns]
data.columns = ['Volume' if 'volume' in x else 'Volume' if 'VOLUME' in x else x for x in data.columns]
data.columns = ['Date' if 'date' in x else 'Date' if 'DATE' in x else x for x in data.columns]
data.columns = ['Time' if 'time' in x else 'Time' if 'TIME' in x else x for x in data.columns]
if 'Date' in data.columns and 'Time' in data.columns:
data['Date'] = data['Date']+" "+data['Time']
elif 'Time' in data.columns and not 'Date' in data.columns:
data['Date'] = data['Time']
elif 'Date' in data.columns and not 'Time' in data.columns:
pass
try:
df = data[['Date','Open','High','Low', 'Close', 'Volume']]
df.reset_index(drop=True, inplace=True)
df['Date'] = df['Date'].astype(str)
df['Date'] = df['Date'].str.replace(r'-|/', '')
missing = data.isnull().sum().sum()
if missing >=1:
print("The sweeper detected missing values")
print("1: No change")
print("2: Delete them")
print("2: Delete the row containing missing data(s)")
answer = input("How do you want to deal with these missing values? (answer 1, 2 or 3)")
if answer ==1:
pass
if answer ==2:
df = df.dropna()
if answer==3:
df = df.dropna( how='all',
subset=['Date','Open','High','Low', 'Close', 'Volume'])
else:
print("not valid answer")
return df
except KeyError:
#non sense messages
print('Oupsi...seems like someone has cast a spell on your dataset')
print('Checking which column has been bewitched...')
cols = ['Date','Open','High','Low', 'Close', 'Volume']
for col in cols:
if col not in data.columns:
print(col + " is invisible")
data[col] = ""
print("The spell has been successfuly broken!")
df = data[['Date','Open','High','Low', 'Close', 'Volume']]
df.reset_index(drop=True, inplace=True)
df['Date'] = df['Date'].astype(str)
df['Date'] = df['Date'].str.replace(r'-|/', '')
missing = data.isnull().sum().sum()
if missing >=1:
print("The sweeper detected missing values")
print("1: No change")
print("2: Delete them")
print("2: Delete the row containing missing data(s)")
answer = input("How do you want to deal with these missing values? (answer 1, 2 or 3)")
if answer ==1:
pass
if answer ==2:
df = df.dropna()
if answer==3:
df = df.dropna( how='all',
subset=['Date','Open','High','Low', 'Close', 'Volume'])
else:
print("not valid answer")
return df
---------------------------------------------------------------------------------------------------------------
def sweeper_dash(data):
for name in logging.Logger.manager.loggerDict.keys():
logging.getLogger(name).setLevel(logging.CRITICAL)
#non efficient, right?
data.columns = ['Open' if 'open' in x else 'Open' if 'OPEN' in x else x for x in data.columns]
data.columns = ['High' if 'high' in x else 'High' if 'HIGH' in x else x for x in data.columns]
data.columns = ['Low' if 'low' in x else 'Low' if 'LOW' in x else x for x in data.columns]
data.columns = ['Close' if 'close' in x else 'Close' if 'CLOSE' in x else x for x in data.columns]
data.columns = ['Volume' if 'volume' in x else 'Volume' if 'VOLUME' in x else x for x in data.columns]
data.columns = ['Date' if 'date' in x else 'Date' if 'DATE' in x else x for x in data.columns]
data.columns = ['Time' if 'time' in x else 'Time' if 'TIME' in x else x for x in data.columns]
if 'Date' in data.columns and 'Time' in data.columns:
data['Date'] = data['Date']+" "+data['Time']
elif 'Time' in data.columns and not 'Date' in data.columns:
data['Date'] = data['Time']
elif 'Date' in data.columns and not 'Time' in data.columns:
pass
try:
df = data[['Date','Open','High','Low', 'Close', 'Volume']]
df.reset_index(drop=True, inplace=True)
df['Date'] = df['Date'].astype(str)
missing = data.isnull().sum().sum()
if missing >=1:
print("The sweeper detected missing values")
print("1: No change")
print("2: Delete them")
print("2: Delete the row containing missing data(s)")
answer = input("How do you want to deal with these missing values? (answer 1, 2 or 3)")
if answer ==1:
pass
if answer ==2:
df = df.dropna()
if answer==3:
df = df.dropna( how='all',
subset=['Date','Open','High','Low', 'Close', 'Volume'])
else:
print("not valid answer")
return df
except KeyError:
#non sense messages
print('Oupsi...seems like someone has cast a spell on your dataset')
print('Checking which column has been bewitched...')
cols = ['Date','Open','High','Low', 'Close', 'Volume']
for col in cols:
if col not in data.columns:
print(col + " is invisible")
data[col] = ""
print("The spell has been successfuly broken!")
df = data[['Date','Open','High','Low', 'Close', 'Volume']]
df.reset_index(drop=True, inplace=True)
df['Date'] = df['Date'].astype(str)
missing = data.isnull().sum().sum()
if missing >=1:
print("The sweeper detected missing values")
print("1: No change")
print("2: Delete them")
print("2: Delete the row containing missing data(s)")
answer = input("How do you want to deal with these missing values? (answer 1, 2 or 3)")
if answer ==1:
pass
if answer ==2:
df = df.dropna()
if answer==3:
df = df.dropna( how='all',
subset=['Date','Open','High','Low', 'Close', 'Volume'])
else:
print("not valid answer")
return df