EXPERIMENT 1

Example 1: Data Visualization Dataset :- Iris Dataset

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as sns

sns.set(style="white", color_codes=True)

%matplotlib inline

df = pd.read_csv('D:\\Movies\\Iris.csv')

df.head()

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

df.plot(kind="scatter", x="SepalLengthCm", y="SepalWidthCm")

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

sns.jointplot(x="SepalLengthCm", y="SepalWidthCm", data=df, size=5)

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

sns.FacetGrid(df, hue="Species", size=5) \

.map(plt.scatter, "SepalLengthCm", "SepalWidthCm") \

.add.legend()

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

sns.boxplot(x="Species", y="PetalLengthCm", data=df)

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

ax=sns.boxplot(x="Species", y="PetalLengthCm", data=df)

ax=sns.stripplot(x="Species", y="PetalLengthCm", data=df, jitter=True, edgecolor="gray")

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

sns.violinplot(x="Species", y="PetalLengthCm", data=df, size=6)

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

sns.violinplot(x="Species", y="PetalLengthCm", data=df, size=6)

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

sns.pairplot(df.drop("Id", axis=1), hue="Species", size=3)

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

sns.pairplot(df.drop("Id", axis=1), hue="Species", size=3,

diag_kind="kde")

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

df.drop("Id", axis=1) .boxplot(by="Species", figsize=(12,6))

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

from pandas.plotting import andrews_curves

andrews_curves(df.drop("Id", axis=1), "Species")

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

from pandas.plotting import parallel_coordinates

parallel_coordinates(df.drop("Id", axis=1), "Species")

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

from pandas.plotting import radviz

radviz(df.drop("Id", axis=1), "Species")

Example 2:- Data Visualization dataset: San Francisco Salaries

salaries = pd.read_csv(‘./Salaries.csv’)

salaries.info()

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

for col in ['BasePay', 'OvertimePay', 'OtherPay', 'Benefits']:

salaries[col] = pd.to_numeric(salaries[col], errors='coerce')

pay_columns = salaries.columns[3:salaries.columns.get_loc('Year')]

pay_columns=Index(['BasePay, 'OvertimePay', 'OtherPay', 'Benefits', 'TotalPay",'TotalPayBenefits'],

pays_arrangement = list(zip(*(iter(pay_columns),) * 3))

fig, axes = plt.subplots(2,3)

for i in range(len(pays_arrangement)):

for j in range(len(pays_arrangement[i])):

# pass in axes to pandas hist

salaries[pays_arrangement[i][j]].hist(ax=axes[i,j])

# axis objects have a lot of methods for customizing the look of a

plot

axes[i,j].set_title(pays_arrangement[i][j])

plt.show()

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

fig, axes = plt.subplots(2,3)

# set the figure height

fig.set_figheight(5)

fig.set_figwidth(12)

for i in range(len(pays_arrangement)):

for j in range(len(pays_arrangement[i])):

# pass in axes to pandas hist

salaries[pays_arrangement[i][j]].hist(ax=axes[i,j])

axes[i,j].set_title(pays_arrangement[i][j])

# add a row of emptiness between the two rows

plt.subplots_adjust(hspace=1)

# add a row of emptiness between the cols

plt.subplots_adjust(wspace=1)

plt.show()

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

# and here is a cleaner version using tick rotation and plot spacing

fig, axes = plt.subplots(2,3)

# set the figure height

fig.set_figheight(5)

fig.set_figwidth(12)

for i in range(len(pays_arrangement)):

for j in range(len(pays_arrangement[i])):

salaries[pays_arrangement[i][j]].hist(ax=axes[i,j])

axes[i,j].set_title(pays_arrangement[i][j])

# set xticks with these labels,

axes[i,j].set_xticklabels(labels=axes[i,j].get_xticks(),

# with this rotation

rotation=30)

plt.subplots_adjust(hspace=1)

plt.subplots_adjust(wspace=1)

plt.show()

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