Plotting categorical outcome and its associated variables in python using seaborn and matplotlib

Resources and libraries

library(reticulate)

import sys

print(sys.version)

## 3.7.5 (default, Oct 31 2019, 15:18:51) [MSC v.1916 64 bit (AMD64)]

import sys

if not sys.warnoptions:
    import warnings
    warnings.simplefilter("ignore")

import pandas as pd

import matplotlib.pyplot as plt

import matplotlib as mpl

mpl.use('ps') # generate postscript output by default

import seaborn as sb

sb.set_style('whitegrid')

pd.set_option('precision', 3)

pd.set_option('expand_frame_repr', True)

#pd.set_option('max_colwidth', -1)

Data

Structure of the dataset

library(MASS)

data("birthwt")

str(birthwt)

## 'data.frame':    189 obs. of  10 variables:
##  $ low  : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ age  : int  19 33 20 21 18 21 22 17 29 26 ...
##  $ lwt  : int  182 155 105 108 107 124 118 103 123 113 ...
##  $ race : int  2 3 1 1 1 3 1 3 1 1 ...
##  $ smoke: int  0 0 1 1 1 0 0 0 1 1 ...
##  $ ptl  : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ ht   : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ ui   : int  1 0 0 1 1 0 0 0 0 0 ...
##  $ ftv  : int  0 3 1 2 0 0 1 1 1 0 ...
##  $ bwt  : int  2523 2551 2557 2594 2600 2622 2637 2637 2663 2665 ...

Describe the variables

#	variable name	variable label	coded levels
1	low	indicator of birth weight less than 2.5 kg	0, 1
2	age	mother’s age in years	continous variable
3	lwt	mother’s weight in pounds at last menstrual period	continous variable
4	race	mother’s race (1 = white, 2 = black, 3 = other)	1, 2, 3
5	smoke	smoking status during pregnancy	0, 1
6	ptl	number of previous premature labours	0, 1, 2, 3
7	ht	history of hypertension	0, 1
8	ui	presence of uterine irritability	0, 1
9	ftv	number of physician visits during the first trimester	0, 1, 2, 3, 4, 6
10	bwt	birth weight in grams	continous variable

Outcome variable is low. Its related variables are: age, lwt, race, smoke, ptl, ht, ui and ftv.

Import and glimpse the data

# save the 'birthwt' data as a 'csv' file and import using pandas 'read_csv' function 

pbwt=pd.read_csv('birthwt.csv')

Information about the data set

# information about data set
pbwt.info()

## <class 'pandas.core.frame.DataFrame'>
## RangeIndex: 189 entries, 0 to 188
## Data columns (total 10 columns):
##  #   Column  Non-Null Count  Dtype
## ---  ------  --------------  -----
##  0   low     189 non-null    int64
##  1   age     189 non-null    int64
##  2   lwt     189 non-null    int64
##  3   race    189 non-null    int64
##  4   smoke   189 non-null    int64
##  5   ptl     189 non-null    int64
##  6   ht      189 non-null    int64
##  7   ui      189 non-null    int64
##  8   ftv     189 non-null    int64
##  9   bwt     189 non-null    int64
## dtypes: int64(10)
## memory usage: 14.9 KB

Data types

# data types: integer/object/category/floating-point
pbwt.dtypes

## low      int64
## age      int64
## lwt      int64
## race     int64
## smoke    int64
## ptl      int64
## ht       int64
## ui       int64
## ftv      int64
## bwt      int64
## dtype: object

First five rows of data

pbwt.head()

##    low  age  lwt  race  smoke  ptl  ht  ui  ftv   bwt
## 0    0   19  182     2      0    0   0   1    0  2523
## 1    0   33  155     3      0    0   0   0    3  2551
## 2    0   20  105     1      1    0   0   0    1  2557
## 3    0   21  108     1      1    0   0   1    2  2594
## 4    0   18  107     1      1    0   0   1    0  2600

Last five rows of data

pbwt.tail()

##      low  age  lwt  race  smoke  ptl  ht  ui  ftv   bwt
## 184    1   28   95     1      1    0   0   0    2  2466
## 185    1   14  100     3      0    0   0   0    2  2495
## 186    1   23   94     3      1    0   0   0    0  2495
## 187    1   17  142     2      0    0   1   0    0  2495
## 188    1   21  130     1      1    0   1   0    3  2495

Data shape or dimension

pbwt.shape

## (189, 10)

Columns name

pbwt.columns

## Index(['low', 'age', 'lwt', 'race', 'smoke', 'ptl', 'ht', 'ui', 'ftv', 'bwt'], dtype='object')

Number of columns

len(pbwt.columns)

## 10

Number of observations

len(pbwt)

## 189

Length of a variable

len(pbwt['age'])

## 189

Number of rows

# rows
pbwt.index

## RangeIndex(start=0, stop=189, step=1)

Plotting categorical outcome and its related varables using seaborn

Count plot using seaborn.countplot()

sb.countplot(x='low', data=pbwt, palette='hls')

#plt.xlabel('Low')

#plt.ylabel('Count')

plt.title('Frequency of low')

plt.show()

#f, ax = plt.subplots(figsize=(8, 8))

sb.countplot(x='low', hue="ftv", data=pbwt, palette='hls')

plt.title('Frequency of ftv by low')

plt.show()

# change axis and color

sb.countplot(y='low', hue="ftv", data=pbwt, color='purple')

plt.title('Frequency of ftv by low')

plt.show()

Count plot using seaborn.catplot()

sb.catplot(x="low", kind="count", palette="ch:.25", data=pbwt)

## <seaborn.axisgrid.FacetGrid object at 0x000000002CC4C348>

plt.title('Frequency of low')

plt.show()

# horizontal orientation: change AXIS

sb.catplot(y="low", kind="count", palette="ch:.25", data=pbwt)

## <seaborn.axisgrid.FacetGrid object at 0x000000002D1AA688>

plt.title('Frequency of low')

plt.show()

# adding another variable as hue

sb.catplot( y="low", hue="ftv", kind="count", data=pbwt)

## <seaborn.axisgrid.FacetGrid object at 0x000000002D1F0488>

plt.title('Frequency of ftv by low')

plt.show()

# different color scheme

sb.catplot( y="low", hue="ftv", kind="count", data=pbwt, palette="pastel", edgecolor=".6")

## <seaborn.axisgrid.FacetGrid object at 0x000000002D22E308>

plt.title('Frequency of ftv by low')

plt.show()

Bar plot

# bivariate bar graph with confidence interval

#pbwt[['low', 'race']]=pbwt[['low', 'race']].astype('int64')

sb.catplot(y="low", x='race', data=pbwt, kind="bar")

## <seaborn.axisgrid.FacetGrid object at 0x000000002D2FE708>

plt.title('Frequency of race by low')

plt.show()

# bivariate bar graph without confidence interval

sb.catplot(y="low", x='race', data=pbwt, kind="bar", ci=None)

## <seaborn.axisgrid.FacetGrid object at 0x000000002D1C20C8>

plt.title('Frequency of race by low')

plt.show()

# adding another variable as hue

sb.catplot( x='race', y="low", hue="smoke", kind="bar", data=pbwt)

## <seaborn.axisgrid.FacetGrid object at 0x000000002D2D1A48>

plt.title('Frequency of race by smoke and low')

plt.show()

Point plot

sb.catplot(x='race', y='low', kind='point', data=pbwt)

## <seaborn.axisgrid.FacetGrid object at 0x000000002D3D9748>

plt.title('Frequency of race by low')

plt.show()

# add another variable as hue

sb.catplot(x='race', y='low', hue='smoke', kind='point', data=pbwt)

## <seaborn.axisgrid.FacetGrid object at 0x000000002D40B248>

plt.title('Frequency of race by smoke and low')


plt.show()

# different markers and line styles

sb.catplot(x='race', y='low', hue='smoke', kind='point', data=pbwt, markers=["^", "o"], linestyles=["-", "--"])

## <seaborn.axisgrid.FacetGrid object at 0x000000002D3AEEC8>

plt.title('Frequency of race by smoke and low')

plt.show()

# if you want to provide labels

recode_smoke = {0:'non_smoker', 1:'smoker'}

pbwt['smokel']= pbwt['smoke'].map(recode_smoke)


recode_race = {1:'white', 2:'black', 3:'others'}

pbwt['racel']= pbwt['race'].map(recode_race)


#sb.catplot(x="racel", y="low", hue="smokel", kind="point", data=pbwt)

sb.catplot(x="racel", y="low", hue="smokel", kind="point", data=pbwt, order=['white', 'black', 'others'])

## <seaborn.axisgrid.FacetGrid object at 0x000000002B9AF888>

plt.title('Frequency of race by smoke and low')

plt.show()

Categorical scatter plot

sb.catplot(x="low", y="age", data=pbwt)

## <seaborn.axisgrid.FacetGrid object at 0x000000002E59A8C8>

plt.xlabel('Body weight category')

plt.ylabel('age')

plt.title("Distribution/spread of mother's age by low")

plt.show()

Linear model: Logistic plots

# when the predictor is categorical

sb.lmplot(x="race", y="low", data=pbwt, logistic=True, y_jitter=.03)

## <seaborn.axisgrid.FacetGrid object at 0x000000002C6FB148>

plt.title('Logistic relationship of race with low')

plt.show()

# when the predictor is continuous

sb.lmplot(x="lwt", y="low", data=pbwt, logistic=True, y_jitter=.03)

## <seaborn.axisgrid.FacetGrid object at 0x000000002E570D48>

plt.title('Logistic relationship of lwt with low')

plt.show()

# convert a continuous predictor (age: age less than 30 is given a value of TRUE) to categorical for logistic plotting

pbwt["age_cat"] = (pbwt['age'] / 30) < 1

sb.lmplot(x="age_cat", y="low", data=pbwt, logistic=True, y_jitter=.03)

## <seaborn.axisgrid.FacetGrid object at 0x000000002E5A0948>

plt.title('Logistic relationship of categorized age with low')

plt.show()

# convert a continuous outcome (bwt: bwt less than 2500 is given a value of TRUE) to a categorical outcome for logistic plotting

pbwt["bwt_cat"] = (pbwt['bwt'] / 2500) < 1

sb.lmplot(x="lwt", y="bwt_cat", data=pbwt, logistic=True, y_jitter=.03)

## <seaborn.axisgrid.FacetGrid object at 0x000000002E5A0C88>

plt.title('Logistic relationship of lwt with categorized infant body weight')

plt.show()

Plotting categorical outcome and its related varables using matplotlib

Bar plot

#f, ax = plt.subplots(figsize=(8, 4))

pbwt['low'].value_counts().plot(kind='bar')

plt.xlabel('Body weight category')

plt.ylabel('Frequency')

plt.title('Frequency of low')

plt.show()

# horizontal bar plot

pbwt['low'].value_counts().plot(kind='barh')

plt.title('Frequency of low')

plt.show()

pbwt['low'].value_counts().plot.bar()

plt.title('Frequency of low')

plt.show()

# horizontal bar plot using `barh` following `plot` command

pbwt['low'].value_counts().plot.barh()

plt.title('Frequency of low')

plt.show()

Pie chart

# with legend 

pbwt['low'].value_counts().plot.pie()

#plt.pie(pbwt['low'].value_counts())

plt.legend(['not_low_body_weight', 'low_body_weight'], loc='best')

plt.title('Frequency of low')

plt.show()

# with label

pbwt['low'].value_counts().plot.pie(labels=['not_low_body_weight', 'low_body_weight'])

#plt.pie(pbwt['low'].value_counts(), labels=['not_low_body_weight', 'low_body_weight'])

plt.title('Frequency of low')

plt.show()

pbwt.head()

##    low  age  lwt  race  smoke  ...   bwt      smokel   racel  age_cat  bwt_cat
## 0    0   19  182     2      0  ...  2523  non_smoker   black     True    False
## 1    0   33  155     3      0  ...  2551  non_smoker  others    False    False
## 2    0   20  105     1      1  ...  2557      smoker   white     True    False
## 3    0   21  108     1      1  ...  2594      smoker   white     True    False
## 4    0   18  107     1      1  ...  2600      smoker   white     True    False
## 
## [5 rows x 14 columns]