lOMoAR cPSD| 7367891

CS 3361 data science lab

Ex No 1:
Install Method
Numpy

Numpy is a numerical computing package for mathematics, science, and engineering. Many data
science packages use Numpy as a dependency.

Ex : pip install NumPy

.Ex: pip install pandas

Ex: pip install statsmodels

Output:
 lOMoAR cPSD| 7367891

Ex. No. 2 - Working with Numpy arrays

Example Code:

# importing numpy

module import numpy as

np

# creating list

list = [1, 2, 3,

4]

# creating numpy array

sample_array = np.array(list1)

print("List in python : ", list)

print("Numpy Array in python :", sample_array)

Example:

# importing numpy

module import numpy as

np

# creating list

list_1 = [1, 2, 3, 4]

list_2 = [5, 6, 7, 8]

list_3 = [9, 10, 11, 12]

# creating numpy array

sample_array = np.array([list_1, list_2, list_3])

print("Numpy multi dimensional array in python\n", sample_array)

Ex.No – 3 - Working with Pandas data frames

Code:

import pandas as pd

import numpy as np

sas=pd.Series([1,3,5,np.nan,6])

sas
 lOMoAR cPSD| 7367891

Code:

import pandas as pd

data={'apple': [3,2,0],

'orange' : [3,8,9]}

purchase=pd.DataFrame(data)

purchase

purchase.to_csv('datasciencelab.csv')
 lOMoAR cPSD| 7367891

Ex. No. 4 - Reading data from text files, Excel and the web and exploring various
commands for doing descriptive analytics on the Iris data set.

For Code:

import pandas as pd

data1=pd.read_csv("Iris.csv")

data1.head()
 lOMoAR cPSD| 7367891

data1.info()

data1.describe()

data1.isnull().sum()

data1.shape
 lOMoAR cPSD| 7367891

data = data1.drop_duplicates(subset ="Species",)

data
 lOMoAR cPSD| 7367891

Ex No. 5 - Use the diabetes data set from UCI and Pima Indians Diabetes data
set for performing the following:

a. Univariate analysis: Frequency, Mean, Median, Mode, Variance,

Code:

import pandas as pd

import numpy as np

import statistics as

st # Load the data

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

print(df.shape)

print(df.info())
 lOMoAR cPSD| 7367891

Measures of Central Tendency

Code:

df.mean()

Code:

print(df.loc[:,'Age'].mean())

print(df.loc[:,'Income'].mean())

Median

Code:

df.median()
 lOMoAR cPSD| 7367891

Code:

df.mode()

Code:

df.std()
 lOMoAR cPSD| 7367891

Code:

df.var()

Code:

from scipy.stats import

iqr iqr(df['Age'])
 lOMoAR cPSD| 7367891

Code:

print(df.skew())

Code:

import pandas as pd

df = pd.read_csv(diabetes.csv')

df.head()
 lOMoAR cPSD| 7367891

Code:

import matplotlib.pyplot as

plt import seaborn as sns

sns.set(style='whitegrid', context='notebook')

cols = ['Pregnancies','Glucose','BloodPressure','SkinThickness','Insulin','BMI','DiabetesPedigreeFunction','Age']

Code:

import numpy as np

cm = np.corrcoef(df[cols].values.T)

sns.set(font_scale=1.5)
 lOMoAR cPSD| 7367891

hm = sns.heatmap(cm,cbar=True,annot=True,square=True,fmt='.2f',annot_kws={'size':
15},yticklabels=cols,xticklabels=cols)

plt.show()

Code:

class LinearRegressionGD(object):

def init (self, eta=0.001, n_iter=20):

self.eta = eta

self.n_iter = n_iter

def fit(self, X, y):

self.w_ = np.zeros(1 + X.shape[1])

self.cost_ = []

for i in range(self.n_iter):

output = self.net_input(X)
 lOMoAR cPSD| 7367891

errors = (y - output)

self.w_[1:] += self.eta *

X.T.dot(errors) self.w_[0] += self.eta *

errors.sum() cost = (errors**2).sum() /

2.0 self.cost_.append(cost)

return self

def net_input(self, X):

return np.dot(X, self.w_[1:]) +

self.w_[0] def predict(self, X):

return self.net_input(X)

X = df[['Age']].values

y = df['Pregnancies'].values

from sklearn.preprocessing import

StandardScaler sc_x = StandardScaler()

sc_y = StandardScaler()

X_std =

sc_x.fit_transform(X) y_std =

sc_y.fit_transform(y) lr =

LinearRegressionGD()

lr.fit(X_std, y_std)

plt.plot(range(1, lr.n_iter+1), lr.cost_)

plt.ylabel('SSE')

plt.xlabel('Epoch')

plt.show()
 lOMoAR cPSD| 7367891

Code:

def lin_regplot(X, y, model):

plt.scatter(X, y, c='blue')

plt.plot(X, model.predict(X),

color='red') return None

lin_regplot(X_std, y_std, lr)

plt.xlabel('Age (standardized)')

plt.ylabel('Pregnancies(standardized)')

plt.show()
 lOMoAR cPSD| 7367891

Code:

age_std = sc_x.transform([20])

pregnancy_std =

lr.predict(age_std)

print("Pregnancy: %.3f" %sc_y.inverse_transform(price_std))

print('Slope: %.3f' % lr.w_[1])

C. Multiple Regression analysis:

Code:

from sklearn.model_selection import train_test_split

train_x, test_x, train_y, test_y = train_test_split(X,Y,test_size=0.3,random_state=99)

train_x.shape, train_y.shape

from sklearn.linear_model import

MultipleRegression le = MultipleRegression()

le.fit(train_x,train_y)

y_pred = le.predict(test_x)

y_pred
 lOMoAR cPSD| 7367891

result = pd.DataFrame({'Actual': test_y, 'Predict' : y_pred})

result
 lOMoAR cPSD| 7367891

Code:

print('coefficient', le.coef_)

print('intercept', le.intercept_)

b. Also compare the results of the above analysis for the two data sets

Installing datacompy

pip install datacompy

Details :

datacompy takes two dataframes as input and gives us a human-readable report containing statistics that lets us
know the similarities and dissimilarities between the two dataframes. It will try to join two dataframes either on a
list of join columns, or on indexes.
 lOMoAR cPSD| 7367891

Code:

import datacompy

compare = datacompy.Compare(df1,df2,join_columns=‟acct_id‟, abs_tol=0.0001,

rel_tol=0,df1_name=‟olddiabetes‟,df2_name=‟newdiabetes‟)

print(compare.report())

OUTPUT:
 lOMoAR cPSD| 7367891

Ex.No. 6 Apply and explore various plotting functions on UCI data sets

a. Normal curves
Code:

import numpy as np

import matplotlib.pyplot as plt

# Creating a series of data of in range of 1-50.

x = np.linspace(1,50,200)

#Creating a Function.

def normal_dist(x , mean , sd):

prob_density = (np.pi*sd) *

np.exp(-0.5*((x-mean)/sd)**2) return prob_density

#Calculate mean and Standard deviation.

mean = np.mean(x)

sd = np.std(x)

#Apply function to the data.

pdf = normal_dist(x,mean,sd)

#Plotting the Results

plt.plot(x,pdf , color = 'red')

plt.xlabel('Data points')
 lOMoAR cPSD| 7367891

plt.ylabel('Probability Density')

b. Density and contour plots

import matplotlib.pyplot as

plt import numpy as np

feature_x = np.arange(0, 50, 2)

feature_y = np.arange(0, 50,

3) # Creating 2-D grid of

features

[X, Y] = np.meshgrid(feature_x, feature_y)

fig, ax = plt.subplots(1, 1)

Z = np.cos(X / 2) + np.sin(Y / 4)

# plots contour lines

ax.contour(X, Y, Z)
 lOMoAR cPSD| 7367891

ax.set_title('Contour Plot')

ax.set_xlabel('feature_x')

ax.set_ylabel('feature_y')

plt.show()

c. Correlation and scatter plots

Code:

import pandas as pd

con = pd.read_csv('concrete.csv')

con

list(con.columns)
 lOMoAR cPSD| 7367891

con.head()

con['cement'] = con['cement'].astype('category')

con.describe(include='category')

import seaborn as sns

sns.scatterplot(x="water", y="coarseagg", data=con);

ax = sns.scatterplot(x="water", y="coarseagg", data=con)

ax.set_title("Concrete Strength vs. Fly ash")

ax.set_xlabel("coarseagg");

sns.lmplot(x="water", y="coarseagg", data=con);

d. Histograms:
Creating a Histogram

Code:

from matplotlib import pyplot as

plt import numpy as np

# Creating dataset

a = np.array([22, 87, 5, 43, 56,

73, 55, 54, 11,

20, 51, 5, 79, 31,

27])
 lOMoAR cPSD| 7367891

# Creating histogram

fig, ax = plt.subplots(figsize =(10, 7))

ax.hist(a, bins = [0, 25, 50, 75,

100]) # Show plot

plt.show()

Code:

import matplotlib.pyplot as plt

import numpy as np

from matplotlib import colors

from matplotlib.ticker import PercentFormatter

# Creating dataset

np.random.seed(23685752)

N_points = 10000

n_bins = 20

# Creating distribution
 lOMoAR cPSD| 7367891

x = np.random.randn(N_points)

y = .8 ** x + np.random.randn(10000) +

25 # Creating histogram

fig, axs = plt.subplots(1, 1,figsize =(10, 7),tight_layout =

True) axs.hist(x, bins = n_bins)

# Show plot

plt.show()

e. Three dimensional plotting

Code:

from mpl_toolkits import mplot3d

import numpy as np
 lOMoAR cPSD| 7367891

import matplotlib.pyplot as plt

fig = plt.figure()

# syntax for 3-D projection

ax = plt.axes(projection

='3d') # defining axes

z = np.linspace(0, 1,

100) x = z * np.sin(25 *

z)

y = z * np.cos(25 *

z) c = x + y

ax.scatter(x, y, z, c =

c) # syntax for plotting

ax.set_title('3d Scatter plot')

plt.show()
 lOMoAR cPSD| 7367891

Ex. No7 Visualizing Geographic Data with Basemap

Code:

%matplotlib inline

import numpy as np

import matplotlib.pyplot as plt

from mpl_toolkits.basemap import Basemap

plt.figure(figsize=(8, 8))

m = Basemap(projection='ortho', resolution=None, lat_0=50, lon_0=-100)

m.bluemarble(scale=0.5);

fig = plt.figure(figsize=(8, 8))

m = Basemap(projection='lcc', resolution=None,

width=8E6, height=8E6,

lat_0=45, lon_0=-100,)
 lOMoAR cPSD| 7367891

m.etopo(scale=0.5, alpha=0.5)

# Map (long, lat) to (x, y) for

plotting x, y = m(-122.3, 47.6)

plt.plot(x, y, 'ok', markersize=5)

plt.text(x, y, ' Seattle',

fontsize=12);

from mpl_toolkits.basemap import Basemap

import matplotlib.pyplot as plt

fig = plt.figure(figsize =

(12,12)) m = Basemap()

m.drawcoastlines()

m.drawcoastlines(linewidth=1.0, linestyle='dashed', color='red')

plt.title("Coastlines", fontsize=20)

plt.show()
 lOMoAR cPSD| 7367891

import numpy as np

import pandas as pd

import matplotlib.pyplot as

plt import seaborn as sns

import geopandas as

gpd import shapefile as

shp

from shapely.geometry import Point

sns.set_style('whitegrid')

fp = r'Maps_with_python\india-polygon.shp'

map_df = gpd.read_file(fp)

map_df_copy = gpd.read_file(fp)

plt.plot(map_df , markersize=5)
lOMoAR cPSD| 7367891