5.

b) BIVARIATE ANALYSIS ON DIABETES DATA

(i) BIVARIATE ANALYSIS USING LINEAR REGRESSION

PROGRAM:
import pandas as pd
import statsmodels.api as sm
data=pd.read_csv(“pima_diabetes.csv")
#create correlation matrix
data.corr()

#Bivariate Analysis of Glucose-Insulin features

#define response variable 1
y1= data['Glucose']

#define explanatory variable 1

x1= data[['Insulin']]

#add constant to predictor variables

x1= sm.add_constant(x1)

#fit linear regression model

model1 = sm.OLS(y1, x1).fit()

#view model summary

print(model1.summary())

#Bivariate Analysis of Age-Pregnancies features

#define response variable 2
y2 = data['Age']

#define explanatory variable 2

x2 = data['Pregnancies']
#add constant to predictor variables
x2 = sm.add_constant(x2)

#fit linear regression model model2

= sm.OLS(y2, x2).fit()

#view model summary

print(model2.summary())

#Bivariate Analysis of SkinThickness-BMI features

#define response variable 3
y3 = data['SkinThickness']

#define explanatory variable 3

x3 = data[['BMI']]

#add constant to predictor variables

x3 = sm.add_constant(x3)

#fit linear regression model

Model3 = sm.OLS(y3, x3).fit()

#view model summary

print(model3.summary())
OUTPUT:
a. Correlation Matrix

b. Bivariate Analysis of Glucose-Insulin features

c. Bivariate Analysis of Age-Pregnancies features

d. Bivariate Analysis of SkinThickness-BMI features

(ii) BIVARIATE ANALYSIS USING LOGISTIC REGRESSION

PROGRAM:
# importing libraries
import statsmodels.api as sm
import pandas as pd

# loading the training dataset

data = pd.read_csv('pima_diabetes.csv', index_col = 0)

# defining the dependent and independent variables

Xtrain = data[['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI',
'DiabetesPedigreeFunction','Age']]
ytrain = data[['Outcome']]

# building the model and fitting the data

log_reg = sm.Logit(ytrain, Xtrain).fit()

# printing the summary table

print(log_reg.summary())
OUTPUT:
5.c) MULTIPLE REGRESSION ANALYSIS ON DIABETES DATA

PROGRAM:
# importing modules and packages
import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression
import statsmodels.api as ssm

# importing data
df = pd.read_csv('pima_diabetes.csv')

# creating feature variables

X = df.drop('Outcome', axis=1)
Y = df['Outcome']

X=ssm.add_constant(X) #to add constant value in the model

model= ssm.OLS(Y,X).fit() #fitting the model predictions=
model.summary() #summary of the model predictions
OUTPUT:
6. APPLICATION OF PLOTTING FUNCTIONS ON UCI DATASET

a) NORMAL CURVES

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

import warnings
warnings.simplefilter(action="ignore", category=FutureWarning)

df = pd.read_csv("adult.csv")

#Check the structure of the data df.info()

sns.set(font_scale=1.5)
sns.catplot(x="relationship", y="age", data=df,
kind="point",hue='income',capsize=0.4,ci=None,aspect=2)

# Show plot
plt.xticks(rotation=90) plt.show()

sns.set(font_scale=1)
sns.relplot(x="educational-num", y="hours-per-week",
data=df, kind="line",row='income' , ci=None,
hue="relationship",style="relationship",markers=True,
dashes=False,aspect=2)

# Show plot
plt.show()
OUTPUT:
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 48842 entries, 0 to 48841
Data columns (total 15 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 age 48842 non-null int64
1 workclass 48842 non-null object
2 fnlwgt 48842 non-null int64
3 education 48842 non-null object
4 educational-num 48842 non-null int64
5 marital-status 48842 non-null object
6 occupation 48842 non-null object
7 relationship 48842 non-null object
8 race 48842 non-null object
9 gender 48842 non-null object
10 capital-gain 48842 non-null int64
11 capital-loss 48842 non-null int64
12 hours-per-week 48842 non-null int64
13 native-country 48842 non-null object 14 income 48842 non-null
object dtypes: int64(6), object(9)
memory usage: 5.6+ MB
b) DENSITY AND CONTOUR PLOTS

PROGRAM:
import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

import warnings warnings.simplefilter(action="ignore", category=FutureWarning)

df = pd.read_csv("adult.csv")

# set seaborn style

sns.set_style("white")

#Map a third variable “income” with a hue semantic to show conditional distributions
sns.kdeplot(data=df, x="age", y="educational-num", hue="income")

#Show filled contours

sns.kdeplot(data=df, x="age", y="educational-num", hue="income", fill=True)

sns.kdeplot(data=df, x="age", y="fnlwgt", hue="income")

sns.kdeplot(data=df, x="age", y="fnlwgt", hue="income", fill=True)

sns.kdeplot(data=df, x="age", y="hours-per-week", hue="income")

sns.kdeplot(data=df, x="age", y="hours-per-week", hue="income", fill=True)

c) CORRELATION AND SCATTER PLOTS

PROGRAM:

import numpy as np import

pandas as pd import

matplotlib.pyplot as plt import

seaborn as sns

import warnings

warnings.simplefilter(action="ignore", category=FutureWarning)

df = pd.read_csv("adult.csv")

# set seaborn style

sns.set_style("white")

sns.scatterplot(data=df[0:100], x="educational-num", y="hours-per-week")

sns.scatterplot(data=df[0:100], x="relationship", y="age")

sns.scatterplot(data=df[0:100], x="relationship", y="age", hue="income")

cormat = df.corr()
sns.heatmap(cormat, annot=True);
d) HISTOGRAMS

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

import warnings
warnings.simplefilter(action="ignore", category=FutureWarning)

df = pd.read_csv("adult.csv")

# set seaborn style

sns.set_style("white")

<AxesSubplot:xlabel='hours-per-week', ylabel='Count'>
sns.histplot(data=df[:100], x="hours-per-week", kde=True, color="red")
<AxesSubplot:xlabel='hours-per-week', ylabel='Count'>

sns.distplot(df["hours-per-week"], color="green")
<AxesSubplot:xlabel='hours-per-week', ylabel='Density'>

sns.histplot(data=df, x="hours-per-week", bins=10)

<AxesSubplot:xlabel='hours-per-week', ylabel='Count'>
sns.histplot(data=df[:100], x="hours-per-week", hue="income", multiple="stack")

sns.histplot(data=df[:100], x="age", hue="income", multiple="stack")

<AxesSubplot:xlabel='age', ylabel='Count'>
df.hist(figsize=(12,12), layout=(3,3), sharex=False)
array([[<AxesSubplot:title={'center':'age'}>,
<AxesSubplot:title={'center':'fnlwgt'}>,
<AxesSubplot:title={'center':'educational-num'}>],
[<AxesSubplot:title={'center':'capital-gain'}>,
<AxesSubplot:title={'center':'capital-loss'}>,
<AxesSubplot:title={'center':'hours-per-week'}>],
[<AxesSubplot:>, <AxesSubplot:>, <AxesSubplot:>]], dtype=object)
e) THREE-DIMENSIONAL PLOTTING

PROGRAM:
from matplotlib import pyplot as plt
import numpy as np
import pandas as pd
import plotly.express as px

df = pd.read_csv("adult.csv")

fig = px.scatter_3d(df[:200], x='age', y='capital-gain', z='hours-per-week', color='income')

fig.show()

fig1 = px.scatter_3d(df[:200], x='age', y='educational-num', z='relationship', color='income')

fig1.show()
7 . VISUALIZING GEOGRAPHIC DATA WITH BASEMAP

PROGRAM:
%matplotlib inline
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from mpl_toolkits.basemap import Basemap

cities = pd.read_csv('california_cities.csv')

# Extract the data

lat = cities['latd'].values
lon = cities['longd'].values
population = cities['population_total'].values
area= cities['area_total_km2'].values
# Draw the map background
fig = plt.figure(figsize=(8, 8))
m = Basemap(projection='lcc', resolution='h', lat_0=37.5, lon_0=-119, width=1E6,
height=1.2E6)
m.shadedrelief()
m.drawcoastlines(color='gray')
m.drawcountries(color='gray')
m.drawstates(color='gray')

# scatter city data, with color reflecting population and size reflecting area
m.scatter(lon, lat, latlon=True, c=np.log10(population), s=area, cmap='Reds', alpha=0.5)

# create colorbar and legend

plt.colorbar(label=r'$\log_{10}({\rm population})$') plt.clim(3, 7)

# make legend with dummy points for

a in [100, 300, 500]:
plt.scatter([], [], c='k', alpha=0.5, s=a, label=str(a) + ' km$^2$')
plt.legend(scatterpoints=1, frameon=False, labelspacing=1, loc='lower left')