Using Pandas for Analyzing Data - Visualization

wavedatalab.github.io

%matplotlib inline
import numpy as np
import pandas as pd

Read the csv file of your choice

ver=pd.read_csv("ver.csv")

Plot counts of a specified column using Pandas

ver.loan_purpose_name.value_counts().plot(kind='barh')

<matplotlib.axes._subplots.AxesSubplot at 0x7f84a288acd0>

Bar plot of median values

ver.groupby('agency_abbr')['applicant_income_000s'].agg(np.median).plot(kind = 'bar')

<matplotlib.axes._subplots.AxesSubplot at 0x7f3481f14ed0>

Box plot example

g = sns.factorplot("loan_purpose_name", "loan_amount_000s", "agency_abbr", ver, kind="box",                        
                   palette="PRGn",aspect=2.25)
g.set(ylim=(0, 600))

<seaborn.axisgrid.FacetGrid at 0x7f84a2cf8950>

Bar plot example

sns.factorplot("loan_purpose_name", data=ver, hue="agency_abbr",size=3,aspect=2)

<seaborn.axisgrid.FacetGrid at 0x7f3481b241d0>

Another bar plot example

sns.factorplot("loan_purpose_name", "loan_amount_000s", data=ver, palette="BuPu_d")

<seaborn.axisgrid.FacetGrid at 0x7f3481b24110>

Violin plot example

sns.violinplot(ver["loan_amount_000s"], ver["loan_purpose_name"], color="BuPu_d").set_ylim(0, 800)
sns.despine(left=True);

Violin plot using log amount

sns.violinplot(ver["logloanamt"], ver["loan_purpose_name"], color="BuPu_d").set_ylim(0, 10)
sns.despine(left=True);

Regression plot

sns.regplot("logloanamt", "logincome", data=ver, robust=True, ci=95, color="seagreen")
sns.despine();

Bar plot of median values

sns.factorplot("agency_abbr", "loan_amount_000s", data=ver, palette="PuBu_d", estimator=np.median);

Bar plot example

sns.factorplot("loan_purpose_name", data=ver, hue="action_taken_name");