Table of Contents

• 1  Imports
• 2  Load data
• 3  Numerical and Categorical Plots

Imports

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

%load_ext autoreload
%load_ext watermark

%autoreload 2
%watermark -a "Bhishan Poudel" -d -v -m
%watermark -iv

Bhishan Poudel 2021-07-11 

CPython 3.7.7
IPython 7.22.0

compiler   : Clang 4.0.1 (tags/RELEASE_401/final)
system     : Darwin
release    : 19.6.0
machine    : x86_64
processor  : i386
CPU cores  : 4
interpreter: 64bit
pandas  1.2.4
numpy   1.19.5
seaborn 0.11.0

# my local library
import sys
sys.path.append("/Users/poudel/Dropbox/a00_Bhishan_Modules/")
sys.path.append("/Users/poudel/Dropbox/a00_Bhishan_Modules/bhishan")
from bhishan import bp

Load data

titanic = sns.load_dataset('titanic')
titanic.head()

	survived	pclass	sex	age	sibsp	parch	fare	embarked	class	who	adult_male	deck	embark_town	alive	alone
0	0	3	male	22.0	1	0	7.2500	S	Third	man	True	NaN	Southampton	no	False
1	1	1	female	38.0	1	0	71.2833	C	First	woman	False	C	Cherbourg	yes	False
2	1	3	female	26.0	0	0	7.9250	S	Third	woman	False	NaN	Southampton	yes	True
3	1	1	female	35.0	1	0	53.1000	S	First	woman	False	C	Southampton	yes	False
4	0	3	male	35.0	0	0	8.0500	S	Third	man	True	NaN	Southampton	no	True

Numerical and Categorical Plots

df = titanic

# df.bp.plot_num('age',print_=True,ms='seaborn-darkgrid')
df.bp.plot_num(num='age',print_=True,ms='dark_background')

     count       mean        std   min     25%   50%   75%   max
age  714.0  29.699118  14.526497  0.42  20.125  28.0  38.0  80.0

df.bp.plot_cat('pclass',ms=-1)

df.bp.plot_num_num('age','fare',xticks1=range(0,90,10),ms=-1,
                   xticks2=range(0,600,50),rot=90,figsize=(12,12))

df.bp.plot_num_cat('pclass','sex',save=True,show=True)

df.bp.plot_cat_num('pclass','age',save=True,show=True,ms='fast')

df.bp.plot_cat_cat('pclass','survived',save=True,show=True,ms=-1)

==================================================
Feature: **pclass**
Overall Count: 
    3: 55.11%
    1: 24.24%
    2: 20.65%

Total  **survived_1** distribution:
    1: 39.77%
    3: 34.8%
    2: 25.44%

Per pclass  **survived_1** distribution:
    1: 62.96%
    2: 47.28%
    3: 24.24%