1

1 Importing Data and Data Visualization Task

[18]: import random

import pandas as pd
import matplotlib.pyplot as plt

[19]: data = {
'age': [random.randint(20,60) for _ in range (100)],
'gender': [random.choice(['Male','Female']) for _ in range (100)],
'income': [random.randint(20000,100000) for _ in range (100)],
}
df=pd.DataFrame(data)
df.to_csv('data.csv',index=False)

[20]: data = pd.read_csv('data.csv')

data.head()

[20]: age gender income

0 21 Female 42551
1 46 Male 73093
2 51 Female 98193
3 27 Female 29804
4 37 Male 52151

[10]: data.tail()

[10]: age gender income

95 46 Female 66391
96 39 Female 28883
97 54 Female 23822
98 31 Female 96601
99 48 Female 56378

[13]: plt.hist(data['age'], color = "red", bins = 20)

plt.xlabel('Age')
plt.ylabel('Frequency')
plt.title('Age Distribution')
plt.show()
 2

[14]: plt.bar(data['gender'].unique(), data['gender'].value_counts(), color =␣

,→'pink')

plt.xlabel('Gender')
plt.ylabel('Count')
plt.title('Gender Comparison')
plt.show()

[15]: plt.figure(figsize=(1,2))
plt.bar(data['gender'].unique(), data['gender'].value_counts(), width = 0.4)
 3

plt.xlabel('Gender')
plt.ylabel('Count')
plt.title('Gender Comparison')
plt.show()

[16]: plt.pie(data['gender'].value_counts(), labels=data['gender'].unique(),)

plt.title('Gender Proportion')
plt.show()
 4

[17]: plt.scatter(data['age'], data['income'])

plt.xlabel('Age')
plt.ylabel('Income')
plt.title('Age vs Income')
plt.show()
 5

2 Data Cleaning and Pre-processing Task

[1]: import pandas as pd

import numpy as np
from sklearn.preprocessing import MinMaxScaler,StandardScaler,RobustScaler
from sklearn.preprocessing import LabelEncoder

[5]: data1 = {
'Age': [35, 41, 23, 32, 28, 36, 45, 39, 44, 29],
'Income': [70000, 90000, 50000, 60000, None, 75000, 100000, 80000, 95000,␣
,→55000],

'Date': ['2020-01-01', '2020-01-02', '2020-01-03', '2020-01-04',␣

,→'2020-01-05', '2020-01-06', '2020-01-07', None, '2020-01-09', '2020-01-10'],

'Marital Status': ['Married', 'Single', 'Married', 'Single', 'Married',␣

,→'Single', 'Married', 'Single', 'Married', 'Single'],

'Gender': ['Female', 'Male', 'Male', 'Female', 'Female', 'Male',␣

,→'Female', 'Male', 'Male', 'Female']

df = pd.DataFrame(data1)
df.to_csv('data1.csv',index=False)

[7]: df=pd.read_csv('data1.csv')
print(df)

Age Income Date Marital Status Gender

0 35 70000.0 2020-01-01 Married Female
1 41 90000.0 2020-01-02 Single Male
2 23 50000.0 2020-01-03 Married Male
3 32 60000.0 2020-01-04 Single Female
4 28 NaN 2020-01-05 Married Female
5 36 75000.0 2020-01-06 Single Male
6 45 100000.0 2020-01-07 Married Female
7 39 80000.0 NaN Single Male
8 44 95000.0 2020-01-09 Married Male
9 29 55000.0 2020-01-10 Single Female
[8]: print(df.columns)
print(df.isnull().sum())
print(df)

Index(['Age', 'Income', 'Date', 'Marital Status', 'Gender'], dtype='object')

Age 0
Income 1
Date 1
Marital Status 0
Gender 0
dtype: int64
Age Income Date Marital Status Gender
0 35 70000.0 2020-01-01 Married Female
1 41 90000.0 2020-01-02 Single Male
2 23 50000.0 2020-01-03 Married Male
 6

3 32 60000.0 2020-01-04 Single Female

4 28 NaN 2020-01-05 Married Female
5 36 75000.0 2020-01-06 Single Male
6 45 100000.0 2020-01-07 Married Female
7 39 80000.0 NaN Single Male
8 44 95000.0 2020-01-09 Married Male
9 29 55000.0 2020-01-10 Single Female
[9]: df['Income'].fillna(df['Income'].mean(),inplace=True)
print(df)

Age Income Date Marital Status Gender

0 35 70000.0 2020-01-01 Married Female
1 41 90000.0 2020-01-02 Single Male
2 23 50000.0 2020-01-03 Married Male
3 32 60000.0 2020-01-04 Single Female
4 28 75000.0 2020-01-05 Married Female
5 36 75000.0 2020-01-06 Single Male
6 45 100000.0 2020-01-07 Married Female
7 39 80000.0 NaN Single Male
8 44 95000.0 2020-01-09 Married Male
9 29 55000.0 2020-01-10 Single Female
[10]: df['Date'].fillna(method='ffill',inplace=True)
print(df)

Age Income Date Marital Status Gender

0 35 70000.0 2020-01-01 Married Female
1 41 90000.0 2020-01-02 Single Male
2 23 50000.0 2020-01-03 Married Male
3 32 60000.0 2020-01-04 Single Female
4 28 75000.0 2020-01-05 Married Female
5 36 75000.0 2020-01-06 Single Male
6 45 100000.0 2020-01-07 Married Female
7 39 80000.0 2020-01-07 Single Male
8 44 95000.0 2020-01-09 Married Male
9 29 55000.0 2020-01-10 Single Female
[11]: df.dropna(inplace=True)
print(df)

Age Income Date Marital Status Gender

0 35 70000.0 2020-01-01 Married Female
1 41 90000.0 2020-01-02 Single Male
2 23 50000.0 2020-01-03 Married Male
3 32 60000.0 2020-01-04 Single Female
4 28 75000.0 2020-01-05 Married Female
5 36 75000.0 2020-01-06 Single Male
6 45 100000.0 2020-01-07 Married Female
7 39 80000.0 2020-01-07 Single Male
8 44 95000.0 2020-01-09 Married Male
9 29 55000.0 2020-01-10 Single Female
 7

[12]: df1 = df.drop('Gender',axis=1)

print(df1)

Age Income Date Marital Status

0 35 70000.0 2020-01-01 Married
1 41 90000.0 2020-01-02 Single
2 23 50000.0 2020-01-03 Married
3 32 60000.0 2020-01-04 Single
4 28 75000.0 2020-01-05 Married
5 36 75000.0 2020-01-06 Single
6 45 100000.0 2020-01-07 Married
7 39 80000.0 2020-01-07 Single
8 44 95000.0 2020-01-09 Married
9 29 55000.0 2020-01-10 Single
[13]: df1 = df1 .assign(age_squared=lambda x:x ['Age']**2)
print(df1)

Age Income Date Marital Status age_squared

0 35 70000.0 2020-01-01 Married 1225
1 41 90000.0 2020-01-02 Single 1681
2 23 50000.0 2020-01-03 Married 529
3 32 60000.0 2020-01-04 Single 1024
4 28 75000.0 2020-01-05 Married 784
5 36 75000.0 2020-01-06 Single 1296
6 45 100000.0 2020-01-07 Married 2025
7 39 80000.0 2020-01-07 Single 1521
8 44 95000.0 2020-01-09 Married 1936
9 29 55000.0 2020-01-10 Single 841
[14]: le= LabelEncoder()
df[['Marital Status','Gender']] = df[['Marital Status','Gender']].apply(le.
,→fit_transform)

df

[14]: Age Income Date Marital Status Gender

0 35 70000.0 2020-01-01 0 0
1 41 90000.0 2020-01-02 1 1
2 23 50000.0 2020-01-03 0 1
3 32 60000.0 2020-01-04 1 0
4 28 75000.0 2020-01-05 0 0
5 36 75000.0 2020-01-06 1 1
6 45 100000.0 2020-01-07 0 0
7 39 80000.0 2020-01-07 1 1
8 44 95000.0 2020-01-09 0 1
9 29 55000.0 2020-01-10 1 0

[15]: scaler = MinMaxScaler()

df1['Age'] = scaler.fit_transform(df1[['Age']])
df1
 8

[15]: Age Income Date Marital Status age_squared

0 0.545455 70000.0 2020-01-01 Married 1225
1 0.818182 90000.0 2020-01-02 Single 1681
2 0.000000 50000.0 2020-01-03 Married 529
3 0.409091 60000.0 2020-01-04 Single 1024
4 0.227273 75000.0 2020-01-05 Married 784
5 0.590909 75000.0 2020-01-06 Single 1296
6 1.000000 100000.0 2020-01-07 Married 2025
7 0.727273 80000.0 2020-01-07 Single 1521
8 0.954545 95000.0 2020-01-09 Married 1936
9 0.272727 55000.0 2020-01-10 Single 841

[16]: scaler = StandardScaler()

df1['Age'] = scaler.fit_transform(df1[['Age']])
df1

[16]: Age Income Date Marital Status age_squared

0 -0.029123 70000.0 2020-01-01 Married 1225
1 0.844581 90000.0 2020-01-02 Single 1681
2 -1.776532 50000.0 2020-01-03 Married 529
3 -0.465975 60000.0 2020-01-04 Single 1024
4 -1.048445 75000.0 2020-01-05 Married 784
5 0.116494 75000.0 2020-01-06 Single 1296
6 1.427050 100000.0 2020-01-07 Married 2025
7 0.553346 80000.0 2020-01-07 Single 1521
8 1.281433 95000.0 2020-01-09 Married 1936
9 -0.902828 55000.0 2020-01-10 Single 841
 9

3 Linear Regression

[1]: import numpy as np

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import PolynomialFeatures
from sklearn.compose import ColumnTransformer
from sklearn.linear_model import LinearRegression

[10]: df_sal = pd.read_csv("Position_Salaries.csv")

df_sal.head()

[10]: Position Level Salary

0 Business Analyst 1 45000
1 Junior Consultant 2 50000
2 Senior Consultant 3 60000
3 Manager 4 80000
4 Country Manager 5 110000

[11]: df_sal.describe()

[11]: Level Salary

count 10.00000 10.000000
mean 5.50000 249500.000000
std 3.02765 299373.883668
min 1.00000 45000.000000
25% 3.25000 65000.000000
50% 5.50000 130000.000000
75% 7.75000 275000.000000
max 10.00000 1000000.000000

[13]: plt.title('Salary Distribution Plot')

sns.distplot(df_sal['Salary'])
plt.show()
 10

[14]: plt.scatter(df_sal['Level'], df_sal['Salary'], color='lightcoral')

plt.title('Salary vs level')
plt.xlabel('Level')
plt.ylabel('Salary')
plt.box(False)
plt.show()
 11

[15]: X=df_sal.iloc[:,1:-1].values
y=df_sal.iloc[:,-1].values

[16]: pr= PolynomialFeatures(degree = 4)

X_poly = pr.fit_transform(X)
lr_2 = LinearRegression()
lr_2.fit(X_poly, y)
lr=LinearRegression()
lr.fit(X,y)

[16]: LinearRegression()

[17]: y_pred_lr = lr.predict(X)

y_pred_poly = lr_2.predict(X_poly)

[18]: plt.scatter(X,y,color = 'lightcoral')

plt.plot (X,lr.predict(X),color='firebrick')
plt.title('Real data (Linear Regression)')
plt.xlabel('Positional Level')
plt.ylabel('Salary')
plt.legend(['X/y_pred_lr','X/y'], title = 'Salary/Level', loc = 'best',␣
,→facecolor='white')

plt.box(False)
plt.show()
 12

[20]: plt.scatter(X,y,color = 'lightcoral')

plt.plot (X,lr_2.predict(X_poly),color='firebrick')
plt.title('Real data (Linear Regression)')
plt.xlabel('Positional Level')
plt.ylabel('Salary')
plt.legend(['X/y_pred_lr','X/y'], title = 'Salary/Level', loc = 'best',␣
,→facecolor='white')

plt.box(False)
plt.show()
13
 14

4 Multiple Linear Regression

[1]: from sklearn.linear_model import LinearRegression

import numpy as np
import pandas as pd
import seaborn as sns
from sklearn import preprocessing
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
from sklearn.metrics import r2_score

[3]: c1="advertising.csv"
df=pd.read_csv(c1)
df=pd.DataFrame(df)

[5]: df.shape

[5]: (200, 4)

[6]: df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 200 entries, 0 to 199
Data columns (total 4 columns):
# Column Non-Null Count Dtype
0 TV 200 non-null float64
1 Radio 200 non-null float64
2 Newspaper 200 non-null float64
3 Sales 200 non-null float64
dtypes: float64(4)
memory usage: 6.4 KB
[7]: df.isnull().sum()

[7]: TV 0
Radio 0
Newspaper 0
Sales 0
dtype: int64

[8]: X=df.drop('Sales',axis=1)
y=df['Sales']

[9]: x_train, x_test,y_train, y_test = train_test_split(X,y,test_size = 0.

,→ 3,random_state = 41)

print(x_train.shape)
print(y_train.shape)
print(x_test.shape)
print(y_test.shape)

(140, 3)
 15

(140,)
(60, 3)
(60,)
[10]: model = LinearRegression()
model.fit(x_train , y_train)

[10]: LinearRegression()

[11]: y_pred = model.predict(x_test)

[12]: plt.scatter(y_test, y_pred)

plt.xlabel('Actual Sales')
plt.ylabel('Prediceted Sales')
plt.title('Multile Linear Regression')
lims=[min(min(y_test),min(y_pred)), max(max(y_test), max(y_pred))]
plt.plot(lims, lims, 'k--')
plt.show

[12]:

5 Logistic Regression

[37]: from sklearn.linear_model import LinearRegression

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
import seaborn as sns
import matplotlib as plt
 16

[23]: np.random.seed(123)
n = 1000
age = np.random.randint(20,40,n)
gender = np.random.choice (['male','female'],n)
education = np.random.choice (['high school','college','graduate'],n)
job_level = np.random.choice (['junior','senior'],n)
last_evaluation = np.random.uniform (0.4, 1, n)
average_monthly_hours = np.random.randint (100, 300, n)
time_spend_company = np.random.randint (1, 10, n)
number_of_projects = np.random.randint (1, 7, n)
work_accident = np.random.randint (0, 1, n)
promotion = np.random.choice ([0, 1], n)
salary = np.random.choice (['low', 'medium', 'high'], n)

[24]: work_accident.shape

[24]: (1000,)

[25]: df = pd.DataFrame({
'age':age,
'gender':gender,
'education': education,
'job_level': job_level,
'last_evaluation':last_evaluation,
'average_monthly_hours': average_monthly_hours,
'time_spend_company' :time_spend_company,
'number_of_projects': number_of_projects,
'work_accident' : work_accident,
'promotion' : promotion,
'salary' :salary,})

#save DataFrame as csv file

df.to_csv('Employee.csv', index=False)

[26]: print(df.isnull().sum())

age 0
gender 0
education 0
job_level 0
last_evaluation 0
average_monthly_hours 0
time_spend_company 0
number_of_projects 0
work_accident 0
promotion 0
salary 0
dtype: int64
[27]: df = df.drop(['number_of_projects','gender', 'last_evaluation'],axis=1)
df
 17

[27]: age education job_level average_monthly_hours time_spend_company \

0 33 college junior 174 3
1 22 graduate senior 198 6
2 22 high school senior 185 4
3 26 high school junior 245 9
4 37 college junior 272 8
.. ... ... ... ... ...
995 39 high school senior 224 8
996 32 high school senior 150 5
997 30 college senior 222 2
998 23 college senior 251 7
999 21 college junior 250 2

work_accident promotion salary

0 0 1 high
1 0 0 high
2 0 0 low
3 0 1 medium
4 0 0 medium
.. ... ... ...
995 0 0 low
996 0 1 low
997 0 1 low
998 0 1 high
999 0 1 medium

[1000 rows x 8 columns]

[28]: le= LabelEncoder()

df[['age','education','job_level','salary']] =␣
,→df[['age','education','job_level','salary']].apply(le.fit_transform)

df

[28]: age education job_level average_monthly_hours time_spend_company \

0 13 0 0 174 3
1 2 1 1 198 6
2 2 2 1 185 4
3 6 2 0 245 9
4 17 0 0 272 8
.. ... ... ... ... ...
995 19 2 1 224 8
996 12 2 1 150 5
997 10 0 1 222 2
998 3 0 1 251 7
999 1 0 0 250 2

work_accident promotion salary

0 0 1 0
1 0 0 0
2 0 0 1
3 0 1 2
 18

4 0 0 2
.. ... ... ...
995 0 0 1
996 0 1 1
997 0 1 1
998 0 1 0
999 0 1 2

[1000 rows x 8 columns]

[29]: X=df.drop('promotion',axis=1)
y=df['promotion']

[30]: x_train, x_test,y_train, y_test = train_test_split(X,y,test_size = 0.

,→ 3,random_state = 41)

print(x_train.shape)
print(y_train.shape)
print(x_test.shape)
print(y_test.shape)

(700, 7)
(700,)
(300, 7)
(300,)
[31]: from sklearn.linear_model import LogisticRegression

[32]: model = LogisticRegression()

model.fit(x_train , y_train)

C:\ProgramData\anaconda3\Lib\site-
packages\sklearn\linear_model\_logistic.py:460: ConvergenceWarning: lbfgs failed
to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-
regression
n_iter_i = _check_optimize_result(
[32]: LogisticRegression()

[33]: y_pred = model.predict(x_test)

[34]: from sklearn.metrics import confusion_matrix, classification_report

[35]: print(classification_report(y_test, y_pred))

precision recall f1-score support

0 0.48 0.81 0.60 145

 19

1 0.49 0.17 0.26 155

accuracy 0.48 300

macro avg 0.48 0.49 0.43 300
weighted avg 0.48 0.48 0.42 300

[38]: cm = confusion_matrix (y_test, y_pred)

ax = plt.pyplot.subplot()
sns.heatmap(cm,annot=True, ax=ax, cmap='Blues', fmt='g')
ax.set_xlabel('Predicted labels')
ax.set_ylabel('True labels')
ax.set_title('Confusion Matrix')

plt.pyplot.show()
 20

6 Support Vector Machine Classifier

[22]: from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split
from sklearn import metrics
from sklearn.svm import SVC
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import accuracy_score,f1_score,confusion_matrix,␣
,→classification_report

[11]: iris=load_iris()
X=iris.data
y=iris.target

[12]: data = pd.DataFrame(iris["data"], columns=iris["feature_names"])

[13]: scaler = MinMaxScaler()

X_normalized = scaler.fit_transform(X)

[14]: X_train, X_test, y_train, y_test = train_test_split(X_normalized, y,␣

,→test_size=0.2, random_state=42)

[15]: iris=load_iris()
X=iris.data
y=iris.target

[19]: svm = SVC(kernel = 'linear',gamma = 'scale', shrinking = False)

svm.fit(X_train, y_train)

[19]: SVC(kernel='linear', shrinking=False)

[20]: y_pred = svm.predict(X_test)

[23]: con = confusion_matrix(y_test, y_pred)

print(con)

[[10 0 0]
[ 0 9 0]
[ 0 0 11]]
[24]: clas = classification_report(y_test, y_pred)
print(clas)

precision recall f1-score support

0 1.00 1.00 1.00 10
1 1.00 1.00 1.00 9
2 1.00 1.00 1.00 11
accuracy 1.00 30
macro avg 1.00 1.00 1.00 30
weighted avg 1.00 1.00 1.00 30
 21

7 Naïve Bayes Classifier

[3]: from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split
from sklearn import metrics
from sklearn.naive_bayes import GaussianNB
import pandas as pd
from sklearn.preprocessing import MinMaxScaler

[22]: iris=load_iris()
X=iris.data
y=iris.target

[23]: data = pd.DataFrame(iris["data"], columns=iris["feature_names"])

[24]: scaler = MinMaxScaler()

X_normalized = scaler.fit_transform(X)

[30]: X_train, X_test, y_train, y_test = train_test_split(X_normalized, y,␣

,→test_size=0.4, random_state=42)

[31]: gnb = GaussianNB()

gnb.fit(X_train, y_train)

[31]: GaussianNB()

[32]: y_pred = gnb.predict(X_test)

[33]: con = confusion_matrix(y_test, y_pred)

print(con)

[[23 0 0]
[ 0 18 1]
[ 0 1 17]]
[34]: clas = classification_report(y_test, y_pred)
print(clas)

precision recall f1-score support

0 1.00 1.00 1.00 23
1 0.95 0.95 0.95 19
2 0.94 0.94 0.94 18
accuracy 0.97 60
macro avg 0.96 0.96 0.96 60
weighted avg 0.97 0.97 0.97 60
 22

8 K-Nearest Neighbour Classifier

[13]: from sklearn.neighbors import KNeighborsClassifier

from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
import pandas as pd
from sklearn.preprocessing import MinMaxScaler

[14]: iris=load_iris()
X=iris.data
y=iris.target

[15]: data = pd.DataFrame(iris["data"], columns=iris["feature_names"])

[16]: scaler = MinMaxScaler()

X_normalized = scaler.fit_transform(X)

[58]: X_train, X_test, y_train, y_test = train_test_split(X_normalized, y,␣

,→test_size=0.2, random_state=42)

[59]: from sklearn.datasets import load_iris

from sklearn.preprocessing import MinMaxScaler
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score,f1_score,confusion_matrix,␣
,→classification_report

from sklearn.model_selection import GridSearchCV

[60]: iris=load_iris()
X=iris.data
y=iris.target

[61]: data = pd.DataFrame(iris["data"], columns=iris["feature_names"])

[62]: scaler = MinMaxScaler()

X_normalized = scaler.fit_transform(X)

[63]: X_train, X_test, y_train, y_test = train_test_split(X_normalized, y,␣

,→test_size=0.2, random_state=42)

[64]: knn = KNeighborsClassifier(n_neighbors=7)

knn.fit(X_train, y_train)

[64]: KNeighborsClassifier(n_neighbors=7)

[65]: y_pred = knn.predict(X_test)

[66]: con = confusion_matrix(y_test, y_pred)

print(con)
 23

[[10 0 0]
[ 0 9 0]
[ 0 0 11]]
[67]: clas = classification_report(y_test, y_pred)
print(clas)

precision recall f1-score support

0 1.00 1.00 1.00 10

1 1.00 1.00 1.00 9
2 1.00 1.00 1.00 11

accuracy 1.00 30
macro avg 1.00 1.00 1.00 30
weighted avg 1.00 1.00 1.00 30
 24

9 Decision Tree Classifier

[1]: from sklearn.datasets import load_iris
from sklearn.preprocessing import MinMaxScaler
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import f1_score,confusion_matrix, classification_report

[2]: iris=load_iris()
X=iris.data
y=iris.target

[3]: data = pd.DataFrame(iris["data"], columns=iris["feature_names"])

[4]: scaler = MinMaxScaler()

X_normalized = scaler.fit_transform(X)

[10]: X_train, X_test, y_train, y_test = train_test_split(X_normalized, y,␣

,→test_size=0.4, random_state=42)

[11]: clf = DecisionTreeClassifier()

clf.fit(X_train, y_train)

[11]: DecisionTreeClassifier()

[12]: y_pred = clf.predict(X_test)

[13]: con = confusion_matrix(y_test, y_pred)

print(con)

[[23 0 0]
[ 0 19 0]
[ 0 0 18]]
[14]: clas = classification_report(y_test, y_pred)
print(clas)

precision recall f1-score support

0 1.00 1.00 1.00 23
1 1.00 1.00 1.00 19
2 1.00 1.00 1.00 18
accuracy 1.00 60
macro avg 1.00 1.00 1.00 60
weighted avg 1.00 1.00 1.00 60
 25

10 Clustering

[18]: import numpy as np

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

[19]: df=pd.read_csv('Mall_Customers.csv')

[20]: df.columns

[20]: Index(['CustomerID', 'Genre', 'Age', 'Annual Income (k$)',

'Spending Score (1-100)'],
dtype='object')

[21]: df.head()

[21]: CustomerID Genre Age Annual Income (k$) Spending Score (1-100)
0 1 Male 19 15 39
1 2 Male 21 15 81
2 3 Female 20 16 6
3 4 Female 23 16 77
4 5 Female 31 17 40

[22]: df.drop(['CustomerID','Genre','Age'], axis = 1, inplace=True)

[23]: df.head()

[23]: Annual Income (k$) Spending Score (1-100)

0 15 39
1 15 81
2 16 6
3 16 77
4 17 40

[24]: from sklearn.cluster import KMeans

wcss_list= []
for i in range(1,11):
kmeans=KMeans(n_clusters=i, init='k-means++', random_state=42)
kmeans.fit(df)
wcss_list.append(kmeans.inertia_)
plt.plot(range(1,11), wcss_list)
plt.title('The elbow Method Graph')
plt.xlabel('Number of clusters(k)')
plt.ylabel('wcss_list')
plt.show()
 26

[25]: kmeans=KMeans(n_clusters=5,init ='k-means++',random_state=42)

y_predict=kmeans.fit_predict(df)

[26]: # Re-fit the KMeans model with 5 clusters if needed

kmeans = KMeans(n_clusters=5, init='k-means++', random_state=42)
y_predict = kmeans.fit_predict(df)

# Plotting the clusters

plt.scatter(df.values[y_predict == 0, 0], df.values[y_predict == 0, 1], s =␣
,→100, c = 'blue', label = 'Cluster 1')

plt.scatter(df.values[y_predict == 1, 0], df.values[y_predict == 1, 1], s =␣

,→100, c = 'green', label = 'Cluster 2')

plt.scatter(df.values[y_predict == 2, 0], df.values[y_predict == 2, 1], s =␣

,→100, c = 'red', label = 'Cluster 3')

plt.scatter(df.values[y_predict == 3, 0], df.values[y_predict == 3, 1], s =␣

,→100, c = 'cyan', label = 'Cluster 4')

plt.scatter(df.values[y_predict == 4, 0], df.values[y_predict == 4, 1], s =␣

,→100, c = 'magenta', label = 'Cluster 5')

# Plotting the centroids

plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s =␣
,→300, c = 'yellow', label = 'Centroid')

plt.title('Clusters of customers')
plt.xlabel('Annual Income (k$)')
 27

plt.ylabel('Spending Score (1-100)')

plt.legend()
plt.show()