-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathday6.py
366 lines (202 loc) · 6.13 KB
/
day6.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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
# -*- coding: utf-8 -*-
"""
Created on Fri Oct 1 19:00:19 2021
@author: vikas
"""
import pandas as pd
grades1 = {'subject1': ['A1','B1','A2','A3'],'subject2': ['A2','A1','B2','B3'] }
grades1
df1 = pd.DataFrame(grades1)
df1
grades2 = {'subject3': ['A31','B31','A32','A33'],'subject4': ['A42','A41','B42','B43']}
df2 = pd.DataFrame(grades2)
df2
grades2 = {'subject2': ['A31','B31','A32','A33'],'subject4': ['A42','A41','B42','B43']}
df3 = pd.DataFrame(grades2)
df3
#join
pd.concat([df1,df2], axis=0)
pd.concat([df1,df3], axis=0)
df1
df2
pd.concat([df1,df2], axis=1)
pd.concat([df1,df3], axis=1)
import pandas as pd
pd.concat([df1,df2], ignore_index=True) #index values in order
'''
df =pd.concat([df1,df2], keys=['x','y']) #adding multiple index
df.index.levels[0]
df.index.levels[0][1]
'''
df1
df2
import pandas as pd
grades1 = {'subject1': ['A1','B1','A2','A3'],'subject2': ['A2','A1','B2','B3'] }
df1 = pd.DataFrame(grades1)
grades2 = {'subject3': ['A31','B31','A32','A33'],'subject4': ['A42','A41','B42','B43']}
df2 = pd.DataFrame(grades2)
df = pd.concat([df1, df2], axis=1)
df.iloc[:, 0:-1]
df = df.rename(columns={'subject3':'abc1', 'subject4':'ee'})
df
df[['subject1','subject4']].columns = {'abc', 'a'}
df
df = df.rename(columns={'subject1':'abc', 'subject2':'a'} )
df
import pandas as pd
rollno = pd.Series(range(1,11))
name =[]
for i in range(1,11):
name.append("Student"+str(i))
name
name = ["Student"+str(i) for i in range(1,11)]
name
genderlist = ['M', 'F']
import numpy as np
gender = np.random.choice(a=genderlist, size=10)
gender
marks1 = np.random.randint(0, 100, size=10)
marks1
marks2 = np.random.randint(0, 100, size=10)
marks2
pd5 = pd.DataFrame({'rollno':rollno,'name':name,
'gender':gender, 'marks1':marks1,
'marks2':marks2})
pd5
import pandas as pd
rollno = pd.Series(range(1,1000001))
name =[]
for i in range(1,1000000):
name.append("Student"+str(i))
name
name = ["Student"+str(i) for i in range(1,1000001)]
name
genderlist = ['M', 'F']
import numpy as np
gender = np.random.choice(a=genderlist, size=1000000)
gender
marks1 = np.random.randint(0, 100, size=1000000)
marks1
marks2 = np.random.randint(0, 100, size=1000000)
marks2
pd5 = pd.DataFrame({'rollno':rollno,'name':name,
'gender':gender, 'marks1':marks1,
'marks2':marks2})
pd5.to_csv('Randomdata.csv', index=False)
import pandas as pd
rollno = pd.Series(range(1,11))
name =[]
for i in range(1,11):
name.append("Student"+str(i))
name
name = ["Student"+str(i) for i in range(1,11)]
name
genderlist = ['M', 'F']
import numpy as np
gender = np.random.choice(a=genderlist, size=10)
gender
marks1 = np.random.randint(0, 100, size=10)
marks1
marks2 = np.random.randint(0, 100, size=10)
marks2
pd5 = pd.DataFrame({'rollno':rollno,'name':name,
'gender':gender})
pd5
course = np.random.choice(a=['BBA','MBA','BTECH'], size=10)
course
pd6 = pd.DataFrame({'rollno':rollno, 'course':course, 'marks2':marks2})
pd6
fees = pd.DataFrame({'course':['BBA','MBA','BTECH', 'MTECH'], 'fees':[100000, 200000, 150000, 220000]})
fees
pd5
pd6
fees
pd7 = pd.merge(pd5, pd6)
pd7
fees
pd8 = pd.merge(pd7, fees)
pd8
pd5 = pd5[:5]
pd5
pd6
rollno1 = pd.Series(range(6,16))
pd9 = pd.DataFrame({'rollno':rollno1, 'course':course, 'marks2':marks2})
pd9
pd5
pd10 = pd.merge(pd5, pd9, how='inner')
pd10
pd11 = pd.merge(pd5, pd9, how='outer')
pd11
pd12 = pd.merge(pd5, pd9, how='left')
pd12
pd13 = pd.merge(pd5, pd9, how='right')
pd13
pd14 = pd.DataFrame({'rollno1':rollno1, 'course':course, 'marks2':marks2})
pd14
pd5
pd15 = pd.merge(pd5, pd14, how='inner', left_on='rollno', right_on='rollno1')
pd15
pd15.drop(['rollno1'], axis=1)
import pandas as pd
import numpy as np
rollno = pd.Series(range(1,1001))
rollno
name = pd.Series(["student" + str(i) for i in range(1,1001)])
name
genderlist = ['M','F']
import random
#gender = random.choices(genderlist, k=1000)
gender= np.random.choice(a=genderlist, size=1000,replace=True, p=[.6,.4])
gender
import collections
collections.Counter(gender)
marks1 = np.random.randint(0,100,size=1000)
marks2 = np.random.randint(0,100,size=1000)
fees = np.random.randint(50000,100000,size=1000)
course = np.random.choice(a=['BBA','MBA','BTECH', 'MTech'], size=1000, p=[0.4, 0.5,0.09,0.01])
course
collections.Counter(course)
city = np.random.choice(a=['Delhi', 'Gurugram','Noida','Faridabad'], size=1000, replace=True, p=[.4,.2,.2,.2])
collections.Counter(city)
course = np.random.choice(a=['BBA','MBA','BTECH', 'MTech'], size=1000, p=[0.4, 0.5,0.09,0.01])
pd8 = pd.DataFrame({'rollno':rollno, 'name':name, 'course':course, 'gender':gender, 'marks1':marks1,'marks2':marks2, 'fees':fees,'city':city})
pd8
pd8.head(1)
pd8.columns
pd8.describe()
pd8.shape
pd8['gender'].value_counts()
pd8['course'].value_counts()
pd9 = pd8.groupby('course')
pd9
pd9 = pd8.groupby('course').size()
pd9
pd10 = pd8.groupby('course').count()
pd10
categ = ['course', 'gender','city']
pd11 = pd8[categ]
pd11.head(2)
pd11.groupby(['city', 'gender', 'course']).size()
pd11.groupby(['course','city', 'gender']).size()
pd12 = pd11.groupby(['course']).size()
pd12
pd12 = pd11.groupby(['course']).get_group('MTech')
pd12
pd8.groupby(['city', 'gender', 'course']).sum()
pd8.groupby(['course','city']).agg({"fees": "sum"})
df1 = pd8.groupby(['course','city']).agg({"fees": ["sum","mean",'std'],
"marks1": ["sum","mean",'std']})
df1.to_csv("data.csv")
pd8.groupby('course', as_index=False).agg({"marks1": "sum"})
df1 = pd8.groupby(['course','city'], as_index=True).agg({"fees": ["sum"],
"marks1": ["sum"]})
df1.to_csv("data2.csv")
pd8.to_excel("pd8.xlsx")
pd8.to_excel("pd81.xlsx",sheet_name='pd8', index=False)
#write to more than one sheet in the workbook, it is necessary to specify an ExcelWriter object:
with pd.ExcelWriter(r'D:\ML-Lab\pd8b.xlsx') as writer:
pd8.to_excel(writer, sheet_name='first', index=False)
pd8.to_excel(writer, sheet_name='second')
f1 = open("aa.txt", 'w')
f1 = open("aa.txt", 'r')
pd8.to_excel('pd8b.xlsx', engine='xlsxwriter')