Assignment 5

Name: Divesh Tadimeti

Roll No: SYAIMLA63

CSV DISPLAY

*Do Visit:https://www.mathsisfun.com/data/standard-normal-distribution.html*
For better understanding

Do Visit:https://www.mathsisfun.com/data/standard-normal-distribution.html For better

understanding

from google.colab import drive

drive.mount('/content/drive')

Mounted at /content/drive

/content/drive/MyDrive/Sem-3/Data Science Lab/A5/CSV Files/wine.csv

a) Data Preprocessing operations:

import pandas as pd
from sklearn.preprocessing import MinMaxScaler

# Read the CSV file and handle null values

df = pd.read_csv("/content/drive/MyDrive/Sem-3/Data Science Lab/A5/CSV Files/wine.csv",

df.columns = ["Wine", "Alcohol", "Malic.acid"]

# Check for missing values

missing_values = df.isnull().sum()
print("Missing Values:")
print(missing_values)

# Mean imputation for 'Alcohol' and 'Malic.acid'

df['Alcohol'].fillna(df['Alcohol'].mean(), inplace=True)
df['Malic.acid'].fillna(df['Malic.acid'].mean(), inplace=True)

Missing Values:
Wine 0
Alcohol 0
Malic.acid 0
dtype: int64

b) Data Integration and Data Normalization:

 MIN MAX NORMALIZATION

import pandas as pd
import numpy as np
from sklearn.preprocessing import MinMaxScaler

df = pd.read_csv("/content/wine.csv", usecols=[0, 1, 2])

df.columns = ["Wine", "Alcohol", "Malic.acid"]

scaling = MinMaxScaler()
scaled_data = scaling.fit_transform(df[['Alcohol', 'Malic.acid']])

print(scaled_data)
 [0.53557312 0.52941176]
[0.39920949 0.5026738 ]
[0.71541502 0.48128342]
[0.58498024 0.6631016 ]
[0.51976285 0.5026738 ]
[0.36363636 0.71122995]
[0.76284585 0.80213904]
[0.45256917 0.51336898]
[0.32608696 0.49197861]
[0.34980237 0.59893048]
[0.97035573 0.5828877 ]
[0.62648221 0.59893048]
[0.69960474 0.48128342]
[0.36561265 0.54010695]
[0.66403162 0.73796791]]

df.head()

Wine Alcohol Malic.acid

0 13.20 1.78 2.14

1 13.16 2.36 2.67

2 14.37 1.95 2.50

3 13.24 2.59 2.87

4 14.20 1.76 2.45

Z-SCORE STANDARDIZATION

from sklearn.preprocessing import StandardScaler

scale = StandardScaler()
scale_data=scale.fit_transform(df[['Alcohol',"Malic.acid"]])
print(scale_data)

[[-0.50162433 -0.8244853 ]
[ 0.01802001 1.10768971]
[-0.34931478 0.48793547]
[ 0.22408586 1.83681236]
[-0.5195431 0.3056548 ]
[-0.42098986 0.3056548 ]
[-0.17012708 0.88895292]
[-0.62705572 -0.7151169 ]
[-0.88687789 -0.35055558]
[-0.1611677 -0.24118718]
[-0.77040588 -0.16827492]
[-0.54642125 0.15983027]
[-0.54642125 0.08691801]
[-0.42098986 0.05046188]
[-0.47474617 1.21705811]
[-0.37619294 1.28997038]
[-0.68977141 0.92540905]
[-0.67185264 0.4150232 ]
[ 0.6810145 0.70667226]
 [-0.6360151 -0.31409944]
[ 1.30817146 1.03477745]
[-0.42994925 -0.02245039]
[-0.66289326 0.56084773]
[-0.47474617 0.88895292]
[-0.25972093 3.11277699]
[-0.51058371 0.92540905]
[-0.55538064 -0.8244853 ]
[-0.39411171 1.58161943]
[-0.59121818 -0.56929237]
[-0.75248711 1.21705811]
[-0.60913695 -0.02245039]
[-0.4568274 -0.02245039]
[-0.72560895 1.21705811]
[-0.48370556 1.03477745]
[-0.47474617 0.15983027]
[-0.62705572 1.72744396]
[-0.61809633 0.67021613]
[-0.75248711 -0.97030983]
[ 1.47839977 0.5243916 ]
[-0.56434002 -0.20473105]
[ 1.344009 -0.89739756]
[-0.40307109 0.81604066]
[ 1.46944039 -0.27764331]
[-0.51058371 -0.97030983]
[ 1.5231967 0.26919867]
[ 1.12002437 -0.31409944]
[-0.59121818 -0.89739756]
[-0.28659909 0.12337414]
[-0.54642125 -0.35055558]
[-0.54642125 -1.18904662]
[-0.61809633 0.85249679]
[-0.52850248 0.19628641]
[-0.39411171 1.14414585]
[-0.60017756 -0.42346784]
[-0.54642125 0.34211094]
[-0.57329941 -0.24118718]
[-0.33139601 1.14414585]
[-0 8152028 0 48793547]

Label Encoding
Notes: https://www.geeksforgeeks.org/ml-label-encoding-of-datasets-in-python/

# Import libraries
import numpy as np #Here whatever we import, i.e. after import ex. pandas or numpy are
import pandas as pd

# Import dataset
df = pd.read_csv('/content/drive/MyDrive/Sem-3/Data Science Lab/A5/CSV Files/Iris.csv')
df
 Id SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Species

0 1 5.1 3.5 1.4 0.2 Iris-setosa

1 2 4.9 3.0 1.4 0.2 Iris-setosa

2 3 4.7 3.2 1.3 0.2 Iris-setosa

3 4 4.6 3.1 1.5 0.2 Iris-setosa

4 5 5.0 3.6 1.4 0.2 Iris-setosa

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

145 146 6.7 3.0 5.2 2.3 Iris-virginica

146 147 6.3 2.5 5.0 1.9 Iris-virginica

147 148 6.5 3.0 5.2 2.0 Iris-virginica

148 149 6.2 3.4 5.4 2.3 Iris-virginica

149 150 5.9 3.0 5.1 1.8 Iris-virginica

150 rows × 6 columns

df['Species'].unique() #THis will Print Categorical data

array(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'], dtype=object)

# Import label encoder

from sklearn import preprocessing #Here sklearn is Library , and preprocessing is part o

# label_encoder object knows

# how to understand word labels.
label_encoder = preprocessing.LabelEncoder() #here as preprocessing is library part or

# Encode labels in column 'species'.

df['Species']= label_encoder.fit_transform(df['Species'])

df['Species'].unique()

array([0, 1, 2])

import pandas as pd

df = pd.read_csv('homeprices.csv') #reading csv file

df
 town area price

0 monroe township 2600 550000

1 monroe township 3000 565000

2 monroe township 3200 610000

3 monroe township 3600 680000

4 monroe township 4000 725000

5 west windsor 2600 585000

6 west windsor 2800 615000

7 west windsor 3300 650000

8 west windsor 3600 710000

9 robinsville 2600 575000

10 robinsville 2900 600000

11 robinsville 3100 620000

12 robinsville 3600 695000

dummies = pd.get_dummies(df.town) #dummies is a method /keyword()get_dummies(df.column_d

dummies

monroe township robinsville west windsor

0 1 0 0

1 1 0 0

2 1 0 0

3 1 0 0

4 1 0 0

5 0 0 1

6 0 0 1

7 0 0 1

8 0 0 1

9 0 1 0

10 0 1 0

11 0 1 0

12 0 1 0
#To Concatenate two datas we use pd.concat()
merge = pd.concat([df, dummies], axis= 'columns') #syntax: pandas.concat([var1, var2], a
merge #As we stored dummies in df.

town area price monroe township robinsville west windsor

0 monroe township 2600 550000 1 0 0

1 monroe township 3000 565000 1 0 0

2 monroe township 3200 610000 1 0 0

3 monroe township 3600 680000 1 0 0

4 monroe township 4000 725000 1 0 0

5 west windsor 2600 585000 0 0 1

6 west windsor 2800 615000 0 0 1

7 west windsor 3300 650000 0 0 1

8 west windsor 3600 710000 0 0 1

9 robinsville 2600 575000 0 1 0

10 robinsville 2900 600000 0 1 0

11 robinsville 3100 620000 0 1 0

12 robinsville 3600 695000 0 1 0

final = merge.drop(['town'], axis = 'columns') #as we no more required town along axis:
final #As We have already encoded [monroe township = 0, west windsor = 1, robinsville =
 area price monroe township robinsville west windsor

0 2600 550000 1 0 0

1 3000 565000 1 0 0

2 3200 610000 1 0 0

3 3600 680000 1 0 0

4 4000 725000 1 0 0

5 2600 585000 0 0 1

6 2800 615000 0 0 1