Table of Contents

• 1  Description
• 2  Imports
• 3  Using plotly api in module bhishan

Description

This is an example tutorial to use my module bhishan for the plotly extension for pandas.

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
seaborn 0.11.0
pandas  1.2.4
numpy   1.19.5

# 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

Using plotly api in module bhishan

# print(sns.get_dataset_names())

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

df.bp.freq(['embarked'],style=True)

	embarked	Count	Percent	Cumulative Count	Cumulative Percent
0	S	644	72.44%	644	72.44%
1	C	168	18.90%	812	91.34%
2	Q	77	8.66%	889	100.00%

df.bp.describe()

	Feature	Type	N	Count	Unique	Missing	MissingPct	Zeros	ZerosPct	Ones	OnesPct	mean	std	min	max	25%	50%	75%	Feature2	smallest5	largest5	first5	last5
11	deck	category	891	203	7	688	77.22	0	0.00	0	0.00								deck	['A', 'A', 'A', 'A', 'A']	['G', 'G', 'G', 'G', 'F']	[nan, 'C', nan, 'C', nan]	[nan, 'B', nan, 'C', nan]
3	age	float64	891	714	88	177	19.87	0	0.00	7	0.79	29.70	14.53	0.42	80.00	20.12	28.00	38.00	age	[0.42, 0.67, 0.75, 0.75, 0.83]	[80.0, 74.0, 71.0, 71.0, 70.5]	[22.0, 38.0, 26.0, 35.0, 35.0]	[27.0, 19.0, nan, 26.0, 32.0]
7	embarked	object	891	889	3	2	0.22	0	0.00	0	0.00								embarked	['C', 'C', 'C', 'C', 'C']	['S', 'S', 'S', 'S', 'S']	['S', 'C', 'S', 'S', 'S']	['S', 'S', 'S', 'C', 'Q']
12	embark_town	object	891	889	3	2	0.22	0	0.00	0	0.00								embark_town	['Cherbourg', 'Cherbourg', 'Cherbourg', 'Cherbourg', 'Cherbourg']	['Southampton', 'Southampton', 'Southampton', 'Southampton', 'Southampton']	['Southampton', 'Cherbourg', 'Southampton', 'Southampton', 'Southampton']	['Southampton', 'Southampton', 'Southampton', 'Cherbourg', 'Queenstown']
5	parch	int64	891	891	7	0	0.00	678	76.09	118	13.24	0.38	0.81	0.00	6.00	0.00	0.00	0.00	parch	[0, 0, 0, 0, 0]	[6, 5, 5, 5, 5]	[0, 0, 0, 0, 0]	[0, 0, 2, 0, 0]
4	sibsp	int64	891	891	7	0	0.00	608	68.24	209	23.46	0.52	1.10	0.00	8.00	0.00	0.00	1.00	sibsp	[0, 0, 0, 0, 0]	[8, 8, 8, 8, 8]	[1, 1, 0, 1, 0]	[0, 0, 1, 0, 0]
0	survived	int64	891	891	2	0	0.00	549	61.62	342	38.38	0.38	0.49	0.00	1.00	0.00	0.00	1.00	survived	[0, 0, 0, 0, 0]	[1, 1, 1, 1, 1]	[0, 1, 1, 1, 0]	[0, 1, 0, 1, 0]
10	adult_male	bool	891	891	2	0	0.00	354	39.73	537	60.27								adult_male	[False, False, False, False, False]	[True, True, True, True, True]	[True, False, False, False, True]	[True, False, False, True, True]
14	alone	bool	891	891	2	0	0.00	354	39.73	537	60.27								alone	[False, False, False, False, False]	[True, True, True, True, True]	[False, False, True, False, True]	[True, True, False, True, True]
6	fare	float64	891	891	248	0	0.00	15	1.68	0	0.00	32.20	49.69	0.00	512.33	7.91	14.45	31.00	fare	[0.0, 0.0, 0.0, 0.0, 0.0]	[512.3292, 512.3292, 512.3292, 263.0, 263.0]	[7.25, 71.2833, 7.925, 53.1, 8.05]	[13.0, 30.0, 23.45, 30.0, 7.75]
1	pclass	int64	891	891	3	0	0.00	0	0.00	216	24.24	2.31	0.84	1.00	3.00	2.00	3.00	3.00	pclass	[1, 1, 1, 1, 1]	[3, 3, 3, 3, 3]	[3, 1, 3, 1, 3]	[2, 1, 3, 1, 3]
2	sex	object	891	891	2	0	0.00	0	0.00	0	0.00								sex	['female', 'female', 'female', 'female', 'female']	['male', 'male', 'male', 'male', 'male']	['male', 'female', 'female', 'female', 'male']	['male', 'female', 'female', 'male', 'male']
8	class	category	891	891	3	0	0.00	0	0.00	0	0.00								class	['First', 'First', 'First', 'First', 'First']	['Third', 'Third', 'Third', 'Third', 'Third']	['Third', 'First', 'Third', 'First', 'Third']	['Second', 'First', 'Third', 'First', 'Third']
9	who	object	891	891	3	0	0.00	0	0.00	0	0.00								who	['child', 'child', 'child', 'child', 'child']	['woman', 'woman', 'woman', 'woman', 'woman']	['man', 'woman', 'woman', 'woman', 'man']	['man', 'woman', 'woman', 'man', 'man']
13	alive	object	891	891	2	0	0.00	0	0.00	0	0.00								alive	['no', 'no', 'no', 'no', 'no']	['yes', 'yes', 'yes', 'yes', 'yes']	['no', 'yes', 'yes', 'yes', 'no']	['no', 'yes', 'no', 'yes', 'no']

df.bp.get_duplicate_columns()

[]

df.dtypes

survived         int64
pclass           int64
sex             object
age            float64
sibsp            int64
parch            int64
fare           float64
embarked        object
class           object
who             object
adult_male        bool
deck            object
embark_town     object
alive           object
alone             bool
dtype: object

df1 = pd.DataFrame({'a': range(3),'b':range(1,4),'a_dup':range(3)})
df1

	a	b	a_dup
0	0	1	0
1	1	2	1
2	2	3	2

df1.bp.get_duplicate_columns()

a == a_dup

['a_dup']

df.bp.missing()

Missing values high threshold = 80%

Number of missing values features: 4
cols_missing_high = []
cols_missing_low = ['deck', 'age', 'embarked', 'embark_town']

	Feature	Type	Count	Missing	Zeros	Unique	MissingPct	ZerosPct	count	mean	std	min	25%	50%	75%	max
11	deck	object	891	688	0	7	77.216611	0.000000
3	age	float64	891	177	0	88	19.865320	0.000000	714.000000	29.699118	14.526497	0.420000	20.125000	28.000000	38.000000	80.000000
7	embarked	object	891	2	0	3	0.224467	0.000000
12	embark_town	object	891	2	0	3	0.224467	0.000000