In 

[3]: import pandas as pd

In [4]: import numpy as np

In [3]: mba = pd.read_csv("D:\\Course PPTS\\R Codes\\1 Basis staistics\\mba.csv")

​
#C:\\Users\\Rohit\\Desktop\\Course PPTS\\R Codes\\1 Basis staistics\\mba.csv
​

In [4]: mba

...

In [5]: # number of Rows

len(mba)

...

In [6]: # check the number of columns

len(mba.columns)
​

...

In [7]: mba.shape

...

In [8]: # column Names

mba.columns
​
#in R mba$gmat
#in python mba['gmat']

...

In [9]: # Top rows

mba.head() # will give top 5 rows
​
...

In [10]: # mention number of rows to display

mba.head(10)

...

In [11]: # tail function to bottom rows

mba.tail(6)

...
In [12]: # column information dataset structure
mba.info()

...

In [13]: # Get stats on the columns

mba.describe()
#summary(mba)
#summary(mba$gmat)
​

...

In [14]: mba.describe().transpose()

...

In [15]: mba
​
# del mba['datasrno'] by using delete command
#mba.drop(0) by giving index it will remove the column

...

In [16]: # Rows information

mba[23:27]

...

In [17]: #mba$workex
​
mba['workex']
​
​
​

...

In [18]: mba1 = mba[['workex','gmat']]

mba1

...

In [19]: ​
del mba['Datasrno']
​
mba

...

In [20]: #In R mean(mba)

mba.mean()

...
In [21]: mba.std()

...

In [22]: mba.describe()

...

In [1]: # in R mean(mba$gmat)
​
mba['gmat'].mean()
​

...

In [24]: mba['gmat'].median()
​
#mba['gmat'].mean
#mba['gmat'].mode()
#mba['gmat'].var()
#mba['gmat'].std()
#mba['gmat'].max()
#mba['gmat'].min()
# Range = mba['gmat'].max() - mba['gmat'].min()
...

In [10]: mba['workex'].mode()

...

In [11]: mba['gmat'].var()

...

In [12]: mba['gmat'].std()

...

In [17]: max(mba['gmat'])

...

In [18]: min(mba['gmat'])
...

In [19]: range = max(mba['gmat'])-min(mba['gmat'])

range

...
In [13]: # In R skewness and kurtosis - we have installed e1071 package
​
from scipy.stats import skew
​
skew = skew(mba['gmat'])
skew
#print("skewness value of gmat:",skew)

...

In [13]: from scipy.stats import kurtosis

kurtosis(mba['gmat'])

...

In [14]: from scipy.stats import mode

mode(mba['gmat'])

...

In [1]: from scipy import stats

In [ ]: ​

Categorical Analysis
In [5]: import pandas as pd
In [6]: wbcd = pd.read_csv("D:\\Course\\Python\\Datasets\\wbcd.csv")
wbcd

Out[6]: id diagnosis radius_mean texture_mean perimeter_mean area_mean smoothness_m

0 87139402 B 12.32 12.39 78.85 464.1 0.1

1 8910251 B 10.60 18.95 69.28 346.4 0.0

2 905520 B 11.04 16.83 70.92 373.2 0.1

3 868871 B 11.28 13.39 73.00 384.8 0.1

4 9012568 B 15.19 13.21 97.65 711.8 0.0

... ... ... ... ... ... ...

564 911320502 B 13.17 18.22 84.28 537.3 0.0

565 898677 B 10.26 14.71 66.20 321.6 0.0

566 873885 M 15.28 22.41 98.92 710.6 0.0

567 911201 B 14.53 13.98 93.86 644.2 0.1

568 9012795 M 21.37 15.10 141.30 1386.0 0.1

569 rows × 32 columns

In [3]: wbcd
​
del wbcd['id']

In [4]: wbcd

Out[4]: diagnosis radius_mean texture_mean perimeter_mean area_mean smoothness_mean comp

0 B 12.32 12.39 78.85 464.1 0.10280

1 B 10.60 18.95 69.28 346.4 0.09688

2 B 11.04 16.83 70.92 373.2 0.10770

3 B 11.28 13.39 73.00 384.8 0.11640

4 B 15.19 13.21 97.65 711.8 0.07963

... ... ... ... ... ... ...

564 B 13.17 18.22 84.28 537.3 0.07466

565 B 10.26 14.71 66.20 321.6 0.09882

566 M 15.28 22.41 98.92 710.6 0.09057

567 B 14.53 13.98 93.86 644.2 0.10990

568 M 21.37 15.10 141.30 1386.0 0.10010

569 rows × 31 columns

In [27]: wbcd['diagnosis'].value_counts()

Out[27]: B 357

M 212

Name: diagnosis, dtype: int64

In [28]: freq = pd.crosstab(index=wbcd['diagnosis'], # Make a crosstab

columns="count")
freq
​
# Number of B are 357
# number of M are 212

Out[28]: col_0 count

diagnosis

B 357

M 212

In [29]: freq/freq.sum()
​
# percentage
​
# b = 357 /357 + 212 = 357/569= 62
# m = 212 / 357+212 = 212.569 = 38

Out[29]: col_0 count

diagnosis

B 0.627417

M 0.372583

In [ ]: # 62 % of users have benign Diagnosis

# 38 % of users have Malignant Diagnosis

In [30]: # replace function used to change the label name in the rows
​
wbcd['diagnosis'].replace({"B":"Bengign","M":"Malignant"},inplace=True)

In [31]: wbcd

...

In [7]: # To replace Column names in the dataset

​
wbcd.rename(columns={'radius_mean':'Mean Radius'},inplace=True)
​
​
In [38]: wbcd

Out[38]: Mean
diagnosis texture_mean perimeter_mean area_mean smoothness_mean compactnes
Radius

0 Bengign 12.32 12.39 78.85 464.1 0.10280

1 Bengign 10.60 18.95 69.28 346.4 0.09688

2 Bengign 11.04 16.83 70.92 373.2 0.10770

3 Bengign 11.28 13.39 73.00 384.8 0.11640

4 Bengign 15.19 13.21 97.65 711.8 0.07963

... ... ... ... ... ... ...

564 Bengign 13.17 18.22 84.28 537.3 0.07466

565 Bengign 10.26 14.71 66.20 321.6 0.09882

566 Malignant 15.28 22.41 98.92 710.6 0.09057

567 Bengign 14.53 13.98 93.86 644.2 0.10990

568 Malignant 21.37 15.10 141.30 1386.0 0.10010

569 rows × 31 columns

In [ ]: ​

In [ ]: ​