Pandas Handbook

Made by - Kawshik Kumar Paul

import numpy as np
import pandas as pd

dict1 = {
    "name":['kawshik', 'mim', 'mohona', 'fahim'],
    "marks":[92, 34, 24,17],
    "city":['naogaon', 'barishal', 'mymensingh', 'dhaka']
}

df = pd.DataFrame(dict1)

df

	name	marks	city
0	kawshik	92	naogaon
1	mim	34	barishal
2	mohona	24	mymensingh
3	fahim	17	dhaka

df.to_csv('friends.csv')

df.to_csv('friends_index_false.csv', index=False)

df.head(2)

	name	marks	city
0	kawshik	92	naogaon
1	mim	34	barishal

df.tail(2)

	name	marks	city
2	mohona	24	mymensingh
3	fahim	17	dhaka

df.describe()

	marks
count	4.00000
mean	41.75000
std	34.21866
min	17.00000
25%	22.25000
50%	29.00000
75%	48.50000
max	92.00000

kawshik = pd.read_csv('kawshik.csv')

kawshik

	Train No	Speed	City
0	96859	56	naogaon
1	49494	234	barishal
2	14567	31	mymensingh
3	49678	76	dhaka

kawshik['Speed']

0     56
1    234
2     31
3     76
Name: Speed, dtype: int64

kawshik['Speed'][0]

56

kawshik['Speed'][0] = 50

d:\coding\python\venv\lib\site-packages\ipykernel_launcher.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  """Entry point for launching an IPython kernel.

kawshik

	Train No	Speed	City
0	96859	50	naogaon
1	49494	234	barishal
2	14567	31	mymensingh
3	49678	76	dhaka

kawshik.to_csv('kawshik.csv')

kawshik

	Train No	Speed	City
0	96859	50	naogaon
1	49494	234	barishal
2	14567	31	mymensingh
3	49678	76	dhaka

kawshik.index = ['first', 'second', 'third', 'forth']

kawshik

	Train No	Speed	City
first	96859	50	naogaon
second	49494	234	barishal
third	14567	31	mymensingh
forth	49678	76	dhaka

kawshik['Speed']

first      50
second    234
third      31
forth      76
Name: Speed, dtype: int64

type(kawshik['Speed'])

pandas.core.series.Series

type(kawshik)

pandas.core.frame.DataFrame

type(kawshik['City'])

pandas.core.series.Series

ser = pd.Series(np.random.rand(34))

ser

0     0.408625
1     0.958209
2     0.050102
3     0.943148
4     0.988070
5     0.201819
6     0.021301
7     0.209862
8     0.786548
9     0.685465
10    0.662113
11    0.131019
12    0.879929
13    0.241299
14    0.652830
15    0.736738
16    0.623727
17    0.293467
18    0.554056
19    0.912506
20    0.665680
21    0.118875
22    0.519187
23    0.187080
24    0.261654
25    0.996156
26    0.728173
27    0.505267
28    0.324265
29    0.096287
30    0.449520
31    0.154427
32    0.672149
33    0.902314
dtype: float64

type(ser)

pandas.core.series.Series

newdf = pd.DataFrame(np.random.rand(334, 5), index=np.arange(334))

newdf.head

<bound method NDFrame.head of             0         1         2         3         4
0    0.799405  0.746828  0.119205  0.608367  0.786477
1    0.795904  0.457078  0.432732  0.753908  0.220771
2    0.355519  0.660129  0.693084  0.058004  0.326732
3    0.278972  0.760987  0.535669  0.533717  0.379935
4    0.029968  0.483665  0.278039  0.511621  0.288220
..        ...       ...       ...       ...       ...
329  0.706344  0.611424  0.103477  0.843983  0.877947
330  0.499120  0.638131  0.957900  0.284939  0.221631
331  0.690365  0.246217  0.394901  0.448833  0.517266
332  0.572044  0.055095  0.311525  0.994674  0.135890
333  0.720756  0.880090  0.365951  0.525556  0.764522

[334 rows x 5 columns]>

newdf.tail

<bound method NDFrame.tail of             0         1         2         3         4
0    0.799405  0.746828  0.119205  0.608367  0.786477
1    0.795904  0.457078  0.432732  0.753908  0.220771
2    0.355519  0.660129  0.693084  0.058004  0.326732
3    0.278972  0.760987  0.535669  0.533717  0.379935
4    0.029968  0.483665  0.278039  0.511621  0.288220
..        ...       ...       ...       ...       ...
329  0.706344  0.611424  0.103477  0.843983  0.877947
330  0.499120  0.638131  0.957900  0.284939  0.221631
331  0.690365  0.246217  0.394901  0.448833  0.517266
332  0.572044  0.055095  0.311525  0.994674  0.135890
333  0.720756  0.880090  0.365951  0.525556  0.764522

[334 rows x 5 columns]>

newdf

	0	1	2	3	4
0	0.799405	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.029968	0.483665	0.278039	0.511621	0.288220
...	...	...	...	...	...
329	0.706344	0.611424	0.103477	0.843983	0.877947
330	0.499120	0.638131	0.957900	0.284939	0.221631
331	0.690365	0.246217	0.394901	0.448833	0.517266
332	0.572044	0.055095	0.311525	0.994674	0.135890
333	0.720756	0.880090	0.365951	0.525556	0.764522

334 rows × 5 columns

type(newdf)

pandas.core.frame.DataFrame

newdf.describe()

	0	1	2	3	4
count	334.000000	334.000000	334.000000	334.000000	334.000000
mean	0.513096	0.493616	0.477430	0.480567	0.510105
std	0.286507	0.288004	0.288410	0.287394	0.287044
min	0.009405	0.000872	0.000328	0.002398	0.002146
25%	0.273721	0.246986	0.217492	0.230989	0.279995
50%	0.509766	0.481127	0.471246	0.472999	0.493294
75%	0.769157	0.747412	0.726509	0.729428	0.767157
max	0.996351	0.998968	0.998639	0.999197	0.998879

newdf.dtypes

0    float64
1    float64
2    float64
3    float64
4    float64
dtype: object

newdf[0][0] = "kawshik"

newdf

	0	1	2	3	4
0	kawshik	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220
...	...	...	...	...	...
329	0.706344	0.611424	0.103477	0.843983	0.877947
330	0.49912	0.638131	0.957900	0.284939	0.221631
331	0.690365	0.246217	0.394901	0.448833	0.517266
332	0.572044	0.055095	0.311525	0.994674	0.135890
333	0.720756	0.880090	0.365951	0.525556	0.764522

334 rows × 5 columns

newdf.dtypes

0     object
1    float64
2    float64
3    float64
4    float64
dtype: object

newdf.index

Int64Index([  0,   1,   2,   3,   4,   5,   6,   7,   8,   9,
            ...
            324, 325, 326, 327, 328, 329, 330, 331, 332, 333],
           dtype='int64', length=334)

newdf.columns

RangeIndex(start=0, stop=5, step=1)

newdf.to_numpy()

array([['kawshik', 0.7468280270640056, 0.11920502426756574,
        0.6083674611733413, 0.7864773618903984],
       [0.7959037030131311, 0.45707764926212713, 0.4327318960508558,
        0.7539077119089841, 0.22077067322180044],
       [0.35551882438767723, 0.6601287028473476, 0.6930844521588839,
        0.058003737174239234, 0.326731727999359],
       ...,
       [0.6903648875868753, 0.24621745410772, 0.39490078854755184,
        0.4488328297446289, 0.5172662921371345],
       [0.5720436956060753, 0.05509470369302227, 0.31152468771458264,
        0.9946744429792433, 0.13588963508998675],
       [0.7207556460259394, 0.8800899770480043, 0.3659510118066531,
        0.5255562368227233, 0.7645221099695815]], dtype=object)

newdf[0][0] = 0.3

d:\coding\python\venv\lib\site-packages\ipykernel_launcher.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  """Entry point for launching an IPython kernel.

newdf.head()

	0	1	2	3	4
0	0.3	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220

newdf.to_numpy()

array([[0.3, 0.7468280270640056, 0.11920502426756574, 0.6083674611733413,
        0.7864773618903984],
       [0.7959037030131311, 0.45707764926212713, 0.4327318960508558,
        0.7539077119089841, 0.22077067322180044],
       [0.35551882438767723, 0.6601287028473476, 0.6930844521588839,
        0.058003737174239234, 0.326731727999359],
       ...,
       [0.6903648875868753, 0.24621745410772, 0.39490078854755184,
        0.4488328297446289, 0.5172662921371345],
       [0.5720436956060753, 0.05509470369302227, 0.31152468771458264,
        0.9946744429792433, 0.13588963508998675],
       [0.7207556460259394, 0.8800899770480043, 0.3659510118066531,
        0.5255562368227233, 0.7645221099695815]], dtype=object)

newdf.T

	0	1	2	3	4	5	6	7	8	9	...	324	325	326	327	328	329	330	331	332	333
0	0.3	0.795904	0.355519	0.278972	0.0299681	0.291862	0.834531	0.924205	0.129359	0.633268	...	0.39188	0.937888	0.582301	0.460118	0.0518385	0.706344	0.49912	0.690365	0.572044	0.720756
1	0.746828	0.457078	0.660129	0.760987	0.483665	0.599023	0.431699	0.857907	0.88125	0.467306	...	0.955653	0.972558	0.893083	0.282904	0.103758	0.611424	0.638131	0.246217	0.0550947	0.88009
2	0.119205	0.432732	0.693084	0.535669	0.278039	0.974973	0.474514	0.110374	0.459516	0.650775	...	0.944489	0.86614	0.206613	0.666397	0.222138	0.103477	0.9579	0.394901	0.311525	0.365951
3	0.608367	0.753908	0.0580037	0.533717	0.511621	0.311611	0.0612383	0.762608	0.957592	0.946802	...	0.350729	0.457923	0.697709	0.49848	0.46399	0.843983	0.284939	0.448833	0.994674	0.525556
4	0.786477	0.220771	0.326732	0.379935	0.28822	0.935842	0.900006	0.919642	0.560121	0.0453475	...	0.176602	0.359021	0.479587	0.904971	0.213876	0.877947	0.221631	0.517266	0.13589	0.764522

5 rows × 334 columns

newdf.head()

	0	1	2	3	4
0	0.3	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220

newdf.sort_index(axis=0, ascending=False)

	0	1	2	3	4
333	0.720756	0.880090	0.365951	0.525556	0.764522
332	0.572044	0.055095	0.311525	0.994674	0.135890
331	0.690365	0.246217	0.394901	0.448833	0.517266
330	0.49912	0.638131	0.957900	0.284939	0.221631
329	0.706344	0.611424	0.103477	0.843983	0.877947
...	...	...	...	...	...
4	0.0299681	0.483665	0.278039	0.511621	0.288220
3	0.278972	0.760987	0.535669	0.533717	0.379935
2	0.355519	0.660129	0.693084	0.058004	0.326732
1	0.795904	0.457078	0.432732	0.753908	0.220771
0	0.3	0.746828	0.119205	0.608367	0.786477

334 rows × 5 columns

newdf.sort_index(axis=1, ascending=False)

	4	3	2	1	0
0	0.786477	0.608367	0.119205	0.746828	0.3
1	0.220771	0.753908	0.432732	0.457078	0.795904
2	0.326732	0.058004	0.693084	0.660129	0.355519
3	0.379935	0.533717	0.535669	0.760987	0.278972
4	0.288220	0.511621	0.278039	0.483665	0.0299681
...	...	...	...	...	...
329	0.877947	0.843983	0.103477	0.611424	0.706344
330	0.221631	0.284939	0.957900	0.638131	0.49912
331	0.517266	0.448833	0.394901	0.246217	0.690365
332	0.135890	0.994674	0.311525	0.055095	0.572044
333	0.764522	0.525556	0.365951	0.880090	0.720756

334 rows × 5 columns

type(newdf)

pandas.core.frame.DataFrame

newdf[0]

0            0.3
1       0.795904
2       0.355519
3       0.278972
4      0.0299681
         ...    
329     0.706344
330      0.49912
331     0.690365
332     0.572044
333     0.720756
Name: 0, Length: 334, dtype: object

type(newdf[0])

pandas.core.series.Series

newdf2 = newdf 

newdf2[0][0] = 1705043

d:\coding\python\venv\lib\site-packages\ipykernel_launcher.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  """Entry point for launching an IPython kernel.

newdf

	0	1	2	3	4
0	1705043	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220
...	...	...	...	...	...
329	0.706344	0.611424	0.103477	0.843983	0.877947
330	0.49912	0.638131	0.957900	0.284939	0.221631
331	0.690365	0.246217	0.394901	0.448833	0.517266
332	0.572044	0.055095	0.311525	0.994674	0.135890
333	0.720756	0.880090	0.365951	0.525556	0.764522

334 rows × 5 columns

newdf2 = newdf.copy()

newdf2.head()

	0	1	2	3	4
0	1705043	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220

newdf.head()

	0	1	2	3	4
0	1705043	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220

newdf2[0][0] = 100

d:\coding\python\venv\lib\site-packages\ipykernel_launcher.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  """Entry point for launching an IPython kernel.

newdf.head()

	0	1	2	3	4
0	1705043	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220

newdf.loc[0,0] = 654

newdf.head(2)

	0	1	2	3	4
0	654	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771

newdf.columns = list("ABCDE")

newdf

	A	B	C	D	E
0	654	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220
...	...	...	...	...	...
329	0.706344	0.611424	0.103477	0.843983	0.877947
330	0.49912	0.638131	0.957900	0.284939	0.221631
331	0.690365	0.246217	0.394901	0.448833	0.517266
332	0.572044	0.055095	0.311525	0.994674	0.135890
333	0.720756	0.880090	0.365951	0.525556	0.764522

334 rows × 5 columns

newdf.head(2)

	A	B	C	D	E
0	654	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771

newdf.loc[0,0] = 1705

newdf.head(2)

	A	B	C	D	E	0
0	654	0.746828	0.119205	0.608367	0.786477	1705.0
1	0.795904	0.457078	0.432732	0.753908	0.220771	NaN

newdf.head()

	A	B	C	D	E	0
0	654	0.746828	0.119205	0.608367	0.786477	1705.0
1	0.795904	0.457078	0.432732	0.753908	0.220771	NaN
2	0.355519	0.660129	0.693084	0.058004	0.326732	NaN
3	0.278972	0.760987	0.535669	0.533717	0.379935	NaN
4	0.0299681	0.483665	0.278039	0.511621	0.288220	NaN

newdf.loc[0, 'A'] = 1705

newdf.head()

	A	B	C	D	E	0
0	1705	0.746828	0.119205	0.608367	0.786477	1705.0
1	0.795904	0.457078	0.432732	0.753908	0.220771	NaN
2	0.355519	0.660129	0.693084	0.058004	0.326732	NaN
3	0.278972	0.760987	0.535669	0.533717	0.379935	NaN
4	0.0299681	0.483665	0.278039	0.511621	0.288220	NaN

newdf.drop(0, axis=1)

	A	B	C	D	E
0	1705	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220
...	...	...	...	...	...
329	0.706344	0.611424	0.103477	0.843983	0.877947
330	0.49912	0.638131	0.957900	0.284939	0.221631
331	0.690365	0.246217	0.394901	0.448833	0.517266
332	0.572044	0.055095	0.311525	0.994674	0.135890
333	0.720756	0.880090	0.365951	0.525556	0.764522

334 rows × 5 columns

newdf = newdf.drop(0, axis=1)

newdf.head()

	A	B	C	D	E
0	1705	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220

newdf.loc[[1,2], ['C', 'D']]

	C	D
1	0.432732	0.753908
2	0.693084	0.058004

newdf.head()

	A	B	C	D	E
0	1705	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220

newdf.loc[:, ['C', 'D']]

	C	D
0	0.119205	0.608367
1	0.432732	0.753908
2	0.693084	0.058004
3	0.535669	0.533717
4	0.278039	0.511621
...	...	...
329	0.103477	0.843983
330	0.957900	0.284939
331	0.394901	0.448833
332	0.311525	0.994674
333	0.365951	0.525556

334 rows × 2 columns

newdf.loc[[1,2], :]

	A	B	C	D	E
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732

newdf.loc[newdf['A']<0.3]

	A	B	C	D	E
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220
5	0.291862	0.599023	0.974973	0.311611	0.935842
8	0.129359	0.881250	0.459516	0.957592	0.560121
14	0.100699	0.932347	0.297595	0.477471	0.224610
...	...	...	...	...	...
312	0.221173	0.602139	0.209530	0.193026	0.202523
315	0.142574	0.594299	0.062924	0.867649	0.335347
320	0.186702	0.350780	0.509517	0.094040	0.295364
321	0.237899	0.345210	0.001442	0.100539	0.416182
328	0.0518385	0.103758	0.222138	0.463990	0.213876

93 rows × 5 columns

newdf.loc[(newdf['A']<0.3) & (newdf['C']>0.1)]

	A	B	C	D	E
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220
5	0.291862	0.599023	0.974973	0.311611	0.935842
8	0.129359	0.881250	0.459516	0.957592	0.560121
14	0.100699	0.932347	0.297595	0.477471	0.224610
...	...	...	...	...	...
309	0.19228	0.357623	0.964034	0.040266	0.553172
311	0.0103135	0.776357	0.665863	0.914261	0.589711
312	0.221173	0.602139	0.209530	0.193026	0.202523
320	0.186702	0.350780	0.509517	0.094040	0.295364
328	0.0518385	0.103758	0.222138	0.463990	0.213876

82 rows × 5 columns

newdf.head(2)

	A	B	C	D	E
0	1705	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771

newdf.iloc[0,4]

0.7864773618903984

newdf.iloc[[0,5], [1,2]]

	B	C
0	0.746828	0.119205
5	0.599023	0.974973

newdf.head(3)

	A	B	C	D	E
0	1705	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732

newdf.drop([0])

	A	B	C	D	E
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220
5	0.291862	0.599023	0.974973	0.311611	0.935842
...	...	...	...	...	...
329	0.706344	0.611424	0.103477	0.843983	0.877947
330	0.49912	0.638131	0.957900	0.284939	0.221631
331	0.690365	0.246217	0.394901	0.448833	0.517266
332	0.572044	0.055095	0.311525	0.994674	0.135890
333	0.720756	0.880090	0.365951	0.525556	0.764522

333 rows × 5 columns

newdf.drop(['A', 'C'], axis=1)

	B	D	E
0	0.746828	0.608367	0.786477
1	0.457078	0.753908	0.220771
2	0.660129	0.058004	0.326732
3	0.760987	0.533717	0.379935
4	0.483665	0.511621	0.288220
...	...	...	...
329	0.611424	0.843983	0.877947
330	0.638131	0.284939	0.221631
331	0.246217	0.448833	0.517266
332	0.055095	0.994674	0.135890
333	0.880090	0.525556	0.764522

334 rows × 3 columns

newdf

	A	B	C	D	E
0	1705	0.746828	0.119205	0.608367	0.786477
1	0.795904	0.457078	0.432732	0.753908	0.220771
2	0.355519	0.660129	0.693084	0.058004	0.326732
3	0.278972	0.760987	0.535669	0.533717	0.379935
4	0.0299681	0.483665	0.278039	0.511621	0.288220
...	...	...	...	...	...
329	0.706344	0.611424	0.103477	0.843983	0.877947
330	0.49912	0.638131	0.957900	0.284939	0.221631
331	0.690365	0.246217	0.394901	0.448833	0.517266
332	0.572044	0.055095	0.311525	0.994674	0.135890
333	0.720756	0.880090	0.365951	0.525556	0.764522

334 rows × 5 columns

newdf.drop(['A', 'C'], axis=1, inplace=True)

newdf

	B	D	E
0	0.746828	0.608367	0.786477
1	0.457078	0.753908	0.220771
2	0.660129	0.058004	0.326732
3	0.760987	0.533717	0.379935
4	0.483665	0.511621	0.288220
...	...	...	...
329	0.611424	0.843983	0.877947
330	0.638131	0.284939	0.221631
331	0.246217	0.448833	0.517266
332	0.055095	0.994674	0.135890
333	0.880090	0.525556	0.764522

334 rows × 3 columns

newdf.drop([1, 5], axis=0, inplace=True)

newdf

	B	D	E
0	0.746828	0.608367	0.786477
2	0.660129	0.058004	0.326732
3	0.760987	0.533717	0.379935
4	0.483665	0.511621	0.288220
6	0.431699	0.061238	0.900006
...	...	...	...
329	0.611424	0.843983	0.877947
330	0.638131	0.284939	0.221631
331	0.246217	0.448833	0.517266
332	0.055095	0.994674	0.135890
333	0.880090	0.525556	0.764522

332 rows × 3 columns

newdf.head(3)

	B	D	E
0	0.746828	0.608367	0.786477
2	0.660129	0.058004	0.326732
3	0.760987	0.533717	0.379935

newdf.reset_index()

	index	B	D	E
0	0	0.746828	0.608367	0.786477
1	2	0.660129	0.058004	0.326732
2	3	0.760987	0.533717	0.379935
3	4	0.483665	0.511621	0.288220
4	6	0.431699	0.061238	0.900006
...	...	...	...	...
327	329	0.611424	0.843983	0.877947
328	330	0.638131	0.284939	0.221631
329	331	0.246217	0.448833	0.517266
330	332	0.055095	0.994674	0.135890
331	333	0.880090	0.525556	0.764522

332 rows × 4 columns

newdf.reset_index(drop=True, inplace=True)

newdf.head()

	B	D	E
0	0.746828	0.608367	0.786477
1	0.660129	0.058004	0.326732
2	0.760987	0.533717	0.379935
3	0.483665	0.511621	0.288220
4	0.431699	0.061238	0.900006

newdf['B'].isnull()

0      False
1      False
2      False
3      False
4      False
       ...  
327    False
328    False
329    False
330    False
331    False
Name: B, Length: 332, dtype: bool

newdf['B'] = None

newdf['B'].isnull()

0      True
1      True
2      True
3      True
4      True
       ... 
327    True
328    True
329    True
330    True
331    True
Name: B, Length: 332, dtype: bool

newdf.loc[:, ['B']] = None

newdf

	B	D	E
0	None	0.608367	0.786477
1	None	0.058004	0.326732
2	None	0.533717	0.379935
3	None	0.511621	0.288220
4	None	0.061238	0.900006
...	...	...	...
327	None	0.843983	0.877947
328	None	0.284939	0.221631
329	None	0.448833	0.517266
330	None	0.994674	0.135890
331	None	0.525556	0.764522

332 rows × 3 columns

newdf.loc[:, ['B']] = 56

newdf

	B	D	E
0	56	0.608367	0.786477
1	56	0.058004	0.326732
2	56	0.533717	0.379935
3	56	0.511621	0.288220
4	56	0.061238	0.900006
...	...	...	...
327	56	0.843983	0.877947
328	56	0.284939	0.221631
329	56	0.448833	0.517266
330	56	0.994674	0.135890
331	56	0.525556	0.764522

332 rows × 3 columns

df = pd.DataFrame({"name":['Alfred', 'Batman', 'Catwoman'],
                 "toy":[np.nan, 'Batmobile', 'Bullwhip'],
                  "born":[pd.NaT, pd.Timestamp("1940-04-25"), pd.NaT]
                  })

df

	name	toy	born
0	Alfred	NaN	NaT
1	Batman	Batmobile	1940-04-25
2	Catwoman	Bullwhip	NaT

df.dropna()

	name	toy	born
1	Batman	Batmobile	1940-04-25

df.dropna(how='all')

	name	toy	born
0	Alfred	NaN	NaT
1	Batman	Batmobile	1940-04-25
2	Catwoman	Bullwhip	NaT

df = pd.DataFrame({"name":['Alfred', 'Batman', 'Catwoman'],
                 "toy":[np.nan, np.nan, np.nan],
                  "born":[pd.NaT, pd.Timestamp("1940-04-25"), pd.NaT]
                  })

df

	name	toy	born
0	Alfred	NaN	NaT
1	Batman	NaN	1940-04-25
2	Catwoman	NaN	NaT

df.dropna(how='all', axis=1)

	name	born
0	Alfred	NaT
1	Batman	1940-04-25
2	Catwoman	NaT

df

	name	toy	born
0	Alfred	NaN	NaT
1	Batman	NaN	1940-04-25
2	Catwoman	NaN	NaT

df = pd.DataFrame({"name":['Alfred', 'Batman', 'Alfred'],
                 "toy":[np.nan, 'Batmobile', 'Bullwhip'],
                  "born":[pd.NaT, pd.Timestamp("1940-04-25"), pd.NaT]
                  })

df

	name	toy	born
0	Alfred	NaN	NaT
1	Batman	Batmobile	1940-04-25
2	Alfred	Bullwhip	NaT

df.drop_duplicates()

	name	toy	born
0	Alfred	NaN	NaT
1	Batman	Batmobile	1940-04-25
2	Alfred	Bullwhip	NaT

df.drop_duplicates(axis=1)

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-110-a01ca93282de> in <module>
----> 1 df.drop_duplicates(axis=1)

TypeError: drop_duplicates() got an unexpected keyword argument 'axis'

df.drop_duplicates(subset=['name'])

	name	toy	born
0	Alfred	NaN	NaT
1	Batman	Batmobile	1940-04-25

df

	name	toy	born
0	Alfred	NaN	NaT
1	Batman	Batmobile	1940-04-25
2	Alfred	Bullwhip	NaT

df.drop_duplicates(subset=['name'], keep='first')

	name	toy	born
0	Alfred	NaN	NaT
1	Batman	Batmobile	1940-04-25

df.drop_duplicates(subset=['name'], keep='last')

	name	toy	born
1	Batman	Batmobile	1940-04-25
2	Alfred	Bullwhip	NaT

df.drop_duplicates(subset=['name'], keep=False)

	name	toy	born
1	Batman	Batmobile	1940-04-25

df.shape

(3, 3)

df.info

<bound method DataFrame.info of      name        toy       born
0  Alfred        NaN        NaT
1  Batman  Batmobile 1940-04-25
2  Alfred   Bullwhip        NaT>

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3 entries, 0 to 2
Data columns (total 3 columns):
 #   Column  Non-Null Count  Dtype         
---  ------  --------------  -----         
 0   name    3 non-null      object        
 1   toy     2 non-null      object        
 2   born    1 non-null      datetime64[ns]
dtypes: datetime64[ns](1), object(2)
memory usage: 200.0+ bytes

df['name'].value_counts(dropna=False)

Alfred    2
Batman    1
Name: name, dtype: int64

df['toy'].value_counts(dropna=False)

Batmobile    1
Bullwhip     1
NaN          1
Name: toy, dtype: int64

df['toy'].value_counts(dropna=True)

Batmobile    1
Bullwhip     1
Name: toy, dtype: int64

df.notnull()

	name	toy	born
0	True	False	False
1	True	True	True
2	True	True	False

df.isnull()

	name	toy	born
0	False	True	True
1	False	False	False
2	False	False	True

Excel Sheet Handling

#pip install xlrd

data = pd.read_excel('data.xlsx')

---------------------------------------------------------------------------
XLRDError                                 Traceback (most recent call last)
<ipython-input-125-d4b807c641e9> in <module>
----> 1 data = pd.read_excel('data.xlsx')

d:\coding\python\venv\lib\site-packages\pandas\util\_decorators.py in wrapper(*args, **kwargs)
    294                 )
    295                 warnings.warn(msg, FutureWarning, stacklevel=stacklevel)
--> 296             return func(*args, **kwargs)
    297 
    298         return wrapper

d:\coding\python\venv\lib\site-packages\pandas\io\excel\_base.py in read_excel(io, sheet_name, header, names, index_col, usecols, squeeze, dtype, engine, converters, true_values, false_values, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols)
    302 
    303     if not isinstance(io, ExcelFile):
--> 304         io = ExcelFile(io, engine=engine)
    305     elif engine and engine != io.engine:
    306         raise ValueError(

d:\coding\python\venv\lib\site-packages\pandas\io\excel\_base.py in __init__(self, path_or_buffer, engine)
    865         self._io = stringify_path(path_or_buffer)
    866 
--> 867         self._reader = self._engines[engine](self._io)
    868 
    869     def __fspath__(self):

d:\coding\python\venv\lib\site-packages\pandas\io\excel\_xlrd.py in __init__(self, filepath_or_buffer)
     20         err_msg = "Install xlrd >= 1.0.0 for Excel support"
     21         import_optional_dependency("xlrd", extra=err_msg)
---> 22         super().__init__(filepath_or_buffer)
     23 
     24     @property

d:\coding\python\venv\lib\site-packages\pandas\io\excel\_base.py in __init__(self, filepath_or_buffer)
    351             self.book = self.load_workbook(filepath_or_buffer)
    352         elif isinstance(filepath_or_buffer, str):
--> 353             self.book = self.load_workbook(filepath_or_buffer)
    354         elif isinstance(filepath_or_buffer, bytes):
    355             self.book = self.load_workbook(BytesIO(filepath_or_buffer))

d:\coding\python\venv\lib\site-packages\pandas\io\excel\_xlrd.py in load_workbook(self, filepath_or_buffer)
     35             return open_workbook(file_contents=data)
     36         else:
---> 37             return open_workbook(filepath_or_buffer)
     38 
     39     @property

d:\coding\python\venv\lib\site-packages\xlrd\__init__.py in open_workbook(filename, logfile, verbosity, use_mmap, file_contents, encoding_override, formatting_info, on_demand, ragged_rows, ignore_workbook_corruption)
    168     # files that xlrd can parse don't start with the expected signature.
    169     if file_format and file_format != 'xls':
--> 170         raise XLRDError(FILE_FORMAT_DESCRIPTIONS[file_format]+'; not supported')
    171 
    172     bk = open_workbook_xls(

XLRDError: Excel xlsx file; not supported

data = pd.read_excel('data.xls')

data

	Unnamed: 0	Train No S2	Speed S2	City S2
0	0	1705043	56	naogaon
1	1	49494	234	barishal
2	2	14567	31	mymensingh
3	3	49678	76	dhaka

data = pd.read_excel('data.xls', sheet_name='Sheet1')

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
d:\coding\python\venv\lib\site-packages\xlrd\book.py in sheet_by_name(self, sheet_name)
    465         try:
--> 466             sheetx = self._sheet_names.index(sheet_name)
    467         except ValueError:

ValueError: 'Sheet1' is not in list

During handling of the above exception, another exception occurred:

XLRDError                                 Traceback (most recent call last)
<ipython-input-128-4bb00da9abf3> in <module>
----> 1 data = pd.read_excel('data.xls', sheet_name='Sheet1')

d:\coding\python\venv\lib\site-packages\pandas\util\_decorators.py in wrapper(*args, **kwargs)
    294                 )
    295                 warnings.warn(msg, FutureWarning, stacklevel=stacklevel)
--> 296             return func(*args, **kwargs)
    297 
    298         return wrapper

d:\coding\python\venv\lib\site-packages\pandas\io\excel\_base.py in read_excel(io, sheet_name, header, names, index_col, usecols, squeeze, dtype, engine, converters, true_values, false_values, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols)
    332         skipfooter=skipfooter,
    333         convert_float=convert_float,
--> 334         mangle_dupe_cols=mangle_dupe_cols,
    335     )
    336 

d:\coding\python\venv\lib\site-packages\pandas\io\excel\_base.py in parse(self, sheet_name, header, names, index_col, usecols, squeeze, converters, true_values, false_values, skiprows, nrows, na_values, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols, **kwds)
    924             convert_float=convert_float,
    925             mangle_dupe_cols=mangle_dupe_cols,
--> 926             **kwds,
    927         )
    928 

d:\coding\python\venv\lib\site-packages\pandas\io\excel\_base.py in parse(self, sheet_name, header, names, index_col, usecols, squeeze, dtype, true_values, false_values, skiprows, nrows, na_values, verbose, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols, **kwds)
    437 
    438             if isinstance(asheetname, str):
--> 439                 sheet = self.get_sheet_by_name(asheetname)
    440             else:  # assume an integer if not a string
    441                 sheet = self.get_sheet_by_index(asheetname)

d:\coding\python\venv\lib\site-packages\pandas\io\excel\_xlrd.py in get_sheet_by_name(self, name)
     42 
     43     def get_sheet_by_name(self, name):
---> 44         return self.book.sheet_by_name(name)
     45 
     46     def get_sheet_by_index(self, index):

d:\coding\python\venv\lib\site-packages\xlrd\book.py in sheet_by_name(self, sheet_name)
    466             sheetx = self._sheet_names.index(sheet_name)
    467         except ValueError:
--> 468             raise XLRDError('No sheet named <%r>' % sheet_name)
    469         return self.sheet_by_index(sheetx)
    470 

XLRDError: No sheet named <'Sheet1'>

data

	Unnamed: 0	Train No S2	Speed S2	City S2
0	0	1705043	56	naogaon
1	1	49494	234	barishal
2	2	14567	31	mymensingh
3	3	49678	76	dhaka

data = pd.read_excel('data.xls', sheet_name='Sheet2')

data

	Unnamed: 0	Train No S2	Speed S2	City S2
0	0	1705043	56	naogaon
1	1	49494	234	barishal
2	2	14567	31	mymensingh
3	3	49678	76	dhaka

data.iloc[0, 0] = 1705

data

	Unnamed: 0	Train No S2	Speed S2	City S2
0	1705	1705043	56	naogaon
1	1	49494	234	barishal
2	2	14567	31	mymensingh
3	3	49678	76	dhaka

data.to_excel('data.xls', sheet_name='Sheet2')

#pip install xlwt

data.to_excel('data.xls', sheet_name='Sheet2')

#Sheet1 is no more. It has been deleted for this.