CSC – 310

ADVANCED PYTHON
PROGRAMMING CONTINUOUS
ASSESSMENT-2
ASSIGNMENT:CA2

NAME : SAIRAM AP
UNIQUE ID : E62220002

DEPT: BSc DATA SCIENCE

10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook

In [1]: import pandas as pd

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

In [2]: data = {
'NAME': ['ANJU', 'BOBBY', 'RIA', 'RAM',
'LAXMAN'], 'SCORE 1': [60, 50, 78, 80, 98],
'SCORE 2': [np.nan, 77, 68, np.nan, 50],
'SCORE 3': [55, 45, 68, 90, 50],
'STATE': ['NY', 'TX', np.nan, np.nan, 'CA'],
'EDUCATION': ['HIGH SCHOOL', np.nan, 'COLLEGE', np.nan, 'COLLEGE']
}

In [3]: df = pd.DataFrame(data)

In [4]: df

Out[4]:
NAME SCORE 1 SCORE 2 SCORE 3 STATE EDUCATION

0 ANJU 60 NaN 55 NY HIGH SCHOOL

1 BOBBY 50 77.0 45 TX NaN

2 RIA 78 68.0 68 NaN COLLEGE

3 RAM 80 NaN 90 NaN NaN

4 LAXMAN 98 50.0 50 CA COLLEGE

In [5]: df_dropped =
df.dropna()
print(df_dropped)
NAME SCORE 1 SCORE 2 SCORE 3 STATE EDUCATION
4 LAXMAN 98 50.0 50 CA COLLEGE

In [6]: df_no_missing_scores = df.dropna(subset=['SCORE 1',

'SCORE 2']) print(df_no_missing_scores)

NAME SCORE 1 SCORE 2 SCORE 3 STATE EDUCATION

1 BOBBY 50 77.0 45 TX NaN
2 RIA 78 68.0 68 NaN COLLEGE
4 LAXMAN 98 50.0 50 CA COLLEGE

In [7]: df['STATE'] =
df['STATE'].fillna(method='bfill')
print(df)
NAME SCORE 1 SCORE 2 SCORE 3 STATE EDUCATION
0 ANJU 60 NaN 55 NY HIGH SCHOOL
1 BOBBY 50 77.0 45 TX NaN
2 RIA 78 68.0 68 CA COLLEGE
3 RAM 80 NaN 90 CA NaN
4 LAXMAN 98 50.0 50 CA COLLEGE

1
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [8]: df_filled = df.fillna(method='ffill',
axis=1) print(df_filled)

NAME SCORE 1 SCORE 2 SCORE 3 STATE EDUCATION

0 ANJU 60 60 55 NY HIGH SCHOOL
1 BOBBY 50 77.0 45 TX TX
2 RIA 78 68.0 68 CA COLLEGE
3 RAM 80 80 90 CA CA
4 LAXMAN 98 50.0 50 CA COLLEGE

In [9]: # lab experiment 2

import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import StandardScaler

In [10]: data = {
'NAME': ['ANJU', 'BOBBY', 'RAM',
'RIA', 'LAXMAN'],
'SCORE 1' [60 50 70 80, 75]
: , , , ,
'SCORE 2' [65 77 78 87, 98]
: , , , ,
'SCORE 3' [55 45 68 90, 50
: , , , ]
In [11]: df = pd.DataFrame(data)

In [12]: df_simple_scaling = df[['SCORE 1', 'SCORE 2', 'SCORE 3']].apply(lambda x: x /

x.max()) print(df_simple_scaling)

SCORE 1 SCORE 2 SCORE 3

0 0.7500 0.663265 0.611111
1 0.6250 0.785714 0.500000
2 0.8750 0.795918 0.755556
3 1.0000 0.887755 1.000000
4 0.9375 1.000000 0.555556

In [13]: scaler = MinMaxScaler()

df_min_max = , 'SCORE 2', 'SCORE
pd.DataFrame(scaler.fit_transform(df[['SCORE 1' 3']]), c
print(df_min_max)

SCORE 1 SCORE 2 SCORE 3

0 0.333333 0.000000 0.222222
1 0.000000 0.363636 0.000000
2 0.666667 0.393939 0.511111
3 1.000000 0.666667 1.000000
4 0.833333 1.000000 0.111111

In [14]: scaler = StandardScaler()

df_z_score = , 'SCORE 2', 'SCORE
pd.DataFrame(scaler.fit_transform(df[['SCORE 1' 3']]), c
print(df_z_score)

SCORE SCORE 2 SCORE 3

1
0 - - -0.409126
0.649934 1.453345
1 - - -1.029013
1.578410 0.363336
2 - 0.396728
0.278543 0.272502
3 0.545004 1.760481
1.207020
4 1.544179 -0.719070
0.742781

2
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [15]: scaler = StandardScaler()
df[['SCORE 1', 'SCORE 2', 'SCORE 3']] = scaler.fit_transform(df[['SCORE 1',
'SCORE 2', '
print(df)
NAME SCORE 1 SCORE 2 SCORE 3
0 ANJU -0.649934 -1.453345 -0.409126
1 BOBBY -1.578410 -0.363336 -1.029013
2 RIA 0.278543 -0.272502 0.396728
3 RAM 1.207020 0.545004 1.760481
4 LAXMAN 0.742781 1.544179 -0.719070

3
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [16]: # lab experiment 3

# a. Create an array of even numbers in the interval 120 to 170

even_numbers = np.arange(120,
171, 2) print("Even numbers:",
even_numbers)

# b. Create an array of 10 numbers and update the value at index 5 to 1000

array_b =
np.arange(10)
array_b[5] = 1000
print("Array with updated value at index 5:", array_b)

# c. Create a numpy array named a1 {'apple', 'mango', 'banana', 'mango'}

a1 = np.array(['apple', 'mango', 'banana', 'mango'])
b = a1 == 'mango' # Create Boolean array checking for
'mango' retrieved_mango = a1[b] # Use Boolean array to
retrieve 'mango' print("Boolean array for 'mango':", b)
print("Retrieved values from a1:", retrieved_mango)

# d. Create an array to store Fahrenheit values and convert to Centigrade

fahrenheit_values = np.array([32, 45, 64, 77, 95])
centigrade_values = np.round((fahrenheit_values - 32) *
(5/9), 3) print("Fahrenheit to Centigrade:",
centigrade_values)

# e. Array 'mark' with shape (5, 6) for student marks

mark = np.random.randint(50, 100,
size=(5, 6)) print("\nMark array:\n",
mark)

# i. mark[:,:]
print("\nAll marks:\n", mark[:, :])

# ii. mark[1:,2]
print("\nmark[1:, 2]:\n", mark[1:, 2])

# iii. mark[1:3:1]
print("\nmark[1:3:1]:\n", mark[1:3:1])

# iv. mark[1:3:1,2]
print("\nmark[1:3:1, 2]:\n", mark[1:3:1, 2])

4
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
Even numbers: [120 122 124 126 128 130 132 134 136 138 140 142 144 146 148 150
152 154
156 158 160 162 164 166 168 170]
Array with updated value at index 5: [ 0 1 2 3 4 1000 6 7
8
9]
Boolean array for 'mango': [False True False
True] Retrieved values from a1: ['mango'
'mango']
Fahrenheit to Centigrade: [ 0. 7.222 17.778 25. 35. ]

Mark array:
[[91 69 88 73 55 55]
[76 61 86 69 75 76]
[85 56 56 68 81 92]
[54 95 79 98 97 77]
[78 89 90 67 81 91]]

All marks:
[[91 69 88 73 55 55]
[76 61 86 69 75 76]
[85 56 56 68 81 92]
[54 95 79 98 97 77]
[78 89 90 67 81 91]]

mark[1:, 2]:
[86 56 79 90]

mark[1:3:1]:
[[76 61 86 69 75 76]
[85 56 56 68 81 92]]

mark[1:3:1, 2]:
[86 56]

mark[-1:, 3]:
[67]

5
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook

6
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In
[17]: # lab experiment 4

# Create a DataFrame using the data from the table

data = {
'Courses': ['Spark', 'PySpark', 'Hadoop', 'Python', 'Hadoop', 'PySpark',
'Python', ' 'Fee': [22000, 25000, 23000, 24000, 67000, 13000, 12000, 11000],
'Duration': [30, 50, 55, 40, 60, 50, 10, 20],
'Discount': [1000, 2300, 1000, 1200, 4000, 1300, 1000, 500]
}

# Create DataFrame
df = pd.DataFrame(data)

# i) Group the dataframe based on Courses

grouped = df.groupby('Courses')

# ii) Display the instances present in each group

print("Instances in each group:")
for name, group in
grouped: print(f"\
nGroup: {name}")
print(group)

# iii) Display the max for each group

print("\nMax for each
group:")
print(grouped.max())

# iv) Display the min for each group

print("\nMin for each
group:")
print(grouped.min())

# v) Display the sum of each group

print("\nSum for each
group:")
print(grouped.sum())

# vi) Display the mean of each group

print("\nMean for each
group:")
print(grouped.mean())

# vii) Display the first instance in each group

print("\nFirst instance in each
group:") print(grouped.first())

# viii) Display the last instance in each group

print("\nLast instance in each
group:") print(grouped.last())

# ix) Display the number of unique groups created

print("\nNumber of unique groups
created:") print(grouped.ngroups)

# x) Display the group information

print("\nGroup information:")
grouped.describe().apply(lambda x: x)

# xi) Calculate the sum for the group Spark for the column Fee
spark_sum_fee = grouped['Fee'].sum()['Spark']
print(f"\nSum for the group Spark (Fee column): {spark_sum_fee}")

# xii) Calculate the mean for the group PySpark for the column Duration, Discount
pyspark_mean_duration = grouped['Duration'].mean()
['PySpark'] pyspark_mean_discount =
grouped['Discount'].mean()['PySpark']
print(f"\nMean for the group PySpark (Duration column):
7
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
{pyspark_mean_duration}") print(f"Mean for the group PySpark (Discount
column): {pyspark_mean_discount}")

# xiii) For each group, display the count and min value
print("\nCount and min value for each
group:") grouped_result =
grouped.agg(['count', 'min'])
print(grouped_result)

8
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook

9
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
Instances in group:
each

Group: Hadoop Duration Discount

Courses Fee
2 Hadoop 23000 55 1000
4 Hadoop 67000 60 4000

Group: PySpark
Courses Fee Duratio Discount
n
1 PySpark 50 2300
25000
5 PySpark 50 1300
13000

Group: Python
Course Fee Duration Discount
s
3 24000 40 1200
Python
6 12000 10 1000
Python

Group: Spark
Courses Fee Duration Discount
0 Spark 22000 30 1000
7 Spark 11000 20 500

Max for each group:

Fee Duration Discount
Courses
Hadoop 67000 60 4000
PySpark 25000 50 2300
Python 24000 40 1200
Spark 22000 30 1000

Min for each group:

Fee Duration Discount
Courses
Hadoop 23000 55 1000
PySpark 13000 50 1300
Python 12000 10 1000
Spark 11000 20 500

Sum for each group:

Fee Duration Discount
Courses
Hadoop 90000 115 5000
PySpark 38000 100 3600
Python 36000 50 2200
Spark 33000 50 1500

Mean for each group:

Fe Duratio Discount
Courses e n
Hadoop 45000. 57. 2500.0
0 5
PySpark 19000. 50. 1800.0
0 0
Python 18000. 25. 1100.0
0 0
Spark 16500. 25. 750.0
0 0

First instance in each group:

Fee Duration Discount
Courses
Hadoop 23000 55 1000
PySpark 25000 50 2300

10
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Python 24000 40 Notebook
1200
Spark 22000 30 1000

Last instance in each group:

Fee Duration Discount
Courses
Hadoop 67000 60 4000
PySpark 13000 50 1300
Python 12000 10 1000

11
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
Spark 11000 20 500

Number of unique groups created:

4

Group information:

Sum for the group Spark (Fee column): 33000

Mean for the group PySpark (Duration column): 50.0

Mean for the group PySpark (Discount column): 1800.0

Count and min value for each group:

Fee Duration Discount
count min count min count min
Courses
Hadoop 2 23000 2 55 2 1000
PySpark 2 13000 2 50 2 1300
Python 2 12000 2 10 2 1000
Spark 2 11000 2 20 2 500

In [18]: # lab experiment 5

data = {
'Favorite Subject': ['Python', 'C', 'C++',
'Java'], 'Number of Students': [24, 6, 8, 4]
}

# Create DataFrame
df = pd.DataFrame(data)

localhost:8888/notebooks/ 12/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [19]: # a) Scatter Plot
plt.figure(figsize=(8, 6))
plt.scatter(df['Favorite Subject'], df['Number of Students'],
color='blue', s=100) plt.title('Scatter Plot of Favorite Subjects vs
Number of Students')
plt.xlabel('Favorite
Subject') plt.ylabel('Number
of Students') plt.show()

localhost:8888/notebooks/ 13/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [20]: # b) Bar Chart
plt.figure(figsize=(8, 6))
plt.bar(df['Favorite Subject'], df['Number of Students'],
color='green') plt.title('Bar Chart of Favorite Subjects vs
Number of Students')
plt.xlabel('Favorite
Subject') plt.ylabel('Number
of Students') plt.show()

localhost:8888/notebooks/ 14/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [21]: # c) Histogram
plt.figure(figsize=(8, 6))
plt.hist(df['Number of Students'], bins=4, color='purple',
edgecolor='black') plt.title('Histogram of Number of Students')
plt.xlabel('Number of
Students')
plt.ylabel('Frequency')
plt.show()

localhost:8888/notebooks/ 15/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [22]: # d) Box Plot
plt.figure(figsize=(8, 6))
sns.boxplot(data=df['Number of Students'],
color='cyan') plt.title('Box Plot of Number of
Students')
plt.xlabel('Number of
Students') plt.show()

localhost:8888/notebooks/ 16/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [23]: # e) Pie Chart
plt.figure(figsize=(8, 6))
plt.pie(df['Number of Students'], labels=df['Favorite Subject'], autopct='%1.1f%
%', star plt.title('Pie Chart of Favorite Subjects')
plt.show()

In [24]: # lab experiment 6

data_week1 = [0.0, 12.2, 2.1, 0.0, 20.5, 5.5, 1.0]
data_week2 = [1.1, 11.2, 3.1, 4.1, 21.4, 5.1, 7.1]
days = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']
df_rainfall = pd.DataFrame({
'Day': days,
'Week 1': data_week1,
'Week 2': data_week2
})

localhost:8888/notebooks/ 17/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [25]: plt.figure(figsize=(10, 6))
plt.plot(days, data_week1, marker='o',
label='Week 1') plt.plot(days, data_week2,
marker='o', label='Week 2') plt.title('Weekly
Rainfall Comparison')
plt.xlabel('Day')
plt.ylabel('Rainfall
(mm)') plt.legend()
plt.show()

localhost:8888/notebooks/ 18/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [26]: import seaborn as sns
plt.figure(figsize=(10, 6))
sns.lineplot(x='Day', y='value', hue='variable', data=pd.melt(df_rainfall,
['Day'])) plt.title('Weekly Rainfall Comparison')
plt.xlabel('Day')
plt.ylabel('Rainfall
(mm)') plt.show()

localhost:8888/notebooks/ 19/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [27]: import plotly.express as px
fig = px.line(df_rainfall, x='Day', y=['Week 1', 'Week 2'], title='Weekly
Rainfall Compa fig.show()

Weekly Rainfall Comparison

20

15
value

10

localhost:8888/notebooks/ 20/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [28]: plt.figure(figsize=(8, 6))
plt.boxplot([data_week1, data_week2], labels=['Week 1',
'Week 2']) plt.title('Rainfall Distribution')
plt.ylabel('Rainfall
(mm)') plt.show()

localhost:8888/notebooks/ 21/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [29]: plt.figure(figsize=(8, 6))
sns.boxplot(data=pd.melt(df_rainfall, ['Day']), x='variable',
y='value') plt.title('Rainfall Distribution')
plt.xlabel('Week')
plt.ylabel('Rainfall
(mm)') plt.show()

localhost:8888/notebooks/ 22/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [30]: import plotly.graph_objects as
go fig = go.Figure()
fig.add_trace(go.Box(y=data_week1, name='Week 1'))
fig.add_trace(go.Box(y=data_week2, name='Week 2'))
fig.update_layout(title='Rainfall Distribution', yaxis_title='Rainfall
(mm)') fig.show()

Rainfall Distribution

20

15
Rainfall (mm)

10

In [31]: # lab experiment 7

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score

In [32]: data = pd.read_csv('auto_insurance.csv')

localhost:8888/notebooks/ 23/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In data
[33]:
Out[33]
: months_as_customer age policy_number policy_bind_date policy_state policy_csl policy_deductable

0 328 48 521585 2014-10-17 OH 250/500 1000

1 228 42 342868 2006-06-27 IN 250/500 2000

2 134 29 687698 2000-09-06 OH 100/300 2000

3 256 41 227811 1990-05-25 IL 250/500 2000

4 228 44 367455 2014-06-06 IL 500/1000 1000

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

995 3 38 941851 1991-07-16 OH 500/1000 1000

996 285 41 186934 2014-01-05 IL 100/300 1000

997 130 34 918516 2003-02-17 OH 250/500 500

998 458 62 533940 2011-11-18 IL 500/1000 2000

999 456 60 556080 1996-11-11 OH 250/500 1000

1000 rows × 40 columns

In [34]: data.head(5)

Out[34]:
months_as_customer age policy_number policy_bind_date policy_state policy_csl policy_deductable p

0 328 48 521585 2014-10-17 OH 250/50 1000

0
1 228 42 342868 2006-06-27 IN 250/50 2000
0
2 134 29 687698 2000-09-06 OH 100/30 2000
0
3 256 41 227811 1990-05-25 IL 250/50 2000
0
4 228 44 367455 2014-06-06 IL 500/100 1000
0

5 rows × 40 columns

In [35]: X = data[['months_as_customer', 'age', 'policy_deductable',

'policy_annual_premium', 'um y = data['total_claim_amount']

In [36]: X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,

random_state=42

In [37]: model =
LinearRegression()
model.fit(X_train,
Out[37]: ▾
LinearRegression
LinearRegression

In [38]: y_pred = model.predict(X_test)

localhost:8888/notebooks/ 24/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [39]: mae = mean_absolute_error(y_test,
y_pred) mse =
mean_squared_error(y_test, y_pred)
rmse = mean_squared_error(y_test, y_pred,
squared=False) variance_score = model.score(X_test,
y_test)

In [40]: print(f'MAE: {mae}')

print(f'MSE: {mse}')
print(f'RMSE: {rmse}')
print(f'Variance Score:
{variance_score}') print(f'R^2 Score:
{r2}')
MAE: 7.703215487708803e-
10 MSE:
1.0706986257954323e-18
RMSE: 1.0347456816993402e-09
Variance Score: 1.0
R^2 Score: 1.0

In [41]: import pandas as pd

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report, accuracy_score

In [42]: df = pd.read_csv('Insurance claims

data.csv') df.head(5)

Out[42]:
policy_id subscription_length vehicle_age customer_age region_code region_density segment model

0 POL04536 9.3 1.2 41 C8 8794 C2 M4

0
1 POL01674 8.2 1.8 35 C2 27003 C1 M9
5
2 POL00719 9.5 0.2 44 C8 8794 C2 M4
4
3 POL01814 5.2 0.4 44 C10 73430 A M1
6
4 POL04901 10.1 1.0 56 C13 5410 B2 M5
1

5 rows × 41 columns

In [43]: X = df[['customer_age', 'vehicle_age',

'region_density', 'subscription_length',
'fuel_type', 'ncap_rating',
'is_brake_assist', 'is_central_locking',
'is_power_steering']] y = df['claim_status']

In [44]: X = pd.get_dummies(X, drop_first=True)

In [45]: X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3,

random_state=42

In [46]: model =
LogisticRegression(max_iter=1000)
model.fit(X_train, y_train)
Out[46]:
▾ LogisticRegressi
on
LogisticRegression(max_iter=100
0)

localhost:8888/notebooks/ 25/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [47]: y_pred = model.predict(X_test)
print(classification_report(y_test, y_pred,
zero_division=1)) print(f'Accuracy:
{accuracy_score(y_test, y_pred):.2f}')
precision recall f1-score support

0 0.93 1.00 0.97 16434

1 1.00 0.00 0.00 1144

accuracy 0.93 17578

macro avg 0.97 0.50 0.48 17578
weighted avg 0.94 0.93 0.90 17578

Accuracy: 0.93

In [48]: # lab experiment 8

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.cluster import KMeans
from sklearn.metrics import classification_report

In [49]: iris = load_iris()

X = iris.data
y = iris.target

In [50]: X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3,

random_state=42

In [51]: svm_model = SVC()

svm_model.fit(X_train, y_train)
svm_pred =
svm_model.predict(X_test)
print("SVM Classification
Report")
SVM Classification Report
precision recall f1-score support

0 1.00 1.00 1.00 19

1 1.00 1.00 1.00 13
2 1.00 1.00 1.00 13

accuracy 1.00 45
macro avg 1.00 1.00 1.00 45
weighted 1.00 1.00 1.00 45
avg

localhost:8888/notebooks/ 26/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [52]: knn_model =
KNeighborsClassifier()
knn_model.fit(X_train, y_train)
knn_pred =
knn_model.predict(X_test)
print("KNN Classification
KNN Classification Report
precision recall f1-score support

0 1.00 1.00 1.00 19

1 1.00 1.00 1.00 13
2 1.00 1.00 1.00 13

accuracy 1.00 45
macro avg 1.00 1.00 1.00 45
weighted 1.00 1.00 1.00 45
avg

In [53]: kmeans_model = KMeans(n_clusters=3, n_init='auto',

random_state=42) kmeans_model.fit(X_train)
y_pred_kmeans = kmeans_model.predict(X_test)
y_pred_kmeans_adjusted = np.choose(y_pred_kmeans, [0, 1,
2]).astype(np.int64) print(classification_report(y_test,
y_pred_kmeans_adjusted))
print(f"K-Means Accuracy: {accuracy_score(y_test, y_pred_kmeans_adjusted):.2f}")
precision recall f1-score support

0 0.00 0.00 0.00 19

1 0.00 0.00 0.00 13
2 0.19 0.23 0.21 13

accuracy 0.07 45
macro avg 0.06 0.08 0.07 45
weighted avg 0.05 0.07 0.06 45

K-Means Accuracy: 0.07

C:\Users\divya\anaconda3\Lib\site-packages\sklearn\cluster\_kmeans.py:1436:
UserWarnin g:

KMeans is known to have a memory leak on Windows with MKL, when there are less
chunks t han available threads. You can avoid it by setting the environment
variable OMP_NUM_THR EADS=1.

localhost:8888/notebooks/ 27/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [54]: !pip install tensorflow

localhost:8888/notebooks/ 28/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
Requirement already satisfied: tensorflow in c:\users\divya\anaconda3\lib\site-
packages (2.17.0)
Requirement already satisfied: tensorflow-intel==2.17.0 in c:\users\divya\
anaconda3\lib
\site-packages (from tensorflow) (2.17.0)
Requirement already satisfied: absl-py>=1.0.0 in c:\users\divya\anaconda3\lib\
site-pack ages (from tensorflow-intel==2.17.0->tensorflow) (2.1.0)
Requirement already satisfied: astunparse>=1.6.0 in c:\users\divya\anaconda3\
lib\site-p ackages (from tensorflow-intel==2.17.0->tensorflow) (1.6.3)
Requirement already satisfied: flatbuffers>=24.3.25 in c:\users\divya\
anaconda3\lib\sit e-packages (from tensorflow-intel==2.17.0->tensorflow)
(24.3.25)
Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in c:\users\
divya\an aconda3\lib\site-packages (from tensorflow-intel==2.17.0->tensorflow)
(0.6.0)
Requirement already satisfied: google-pasta>=0.1.1 in c:\users\divya\anaconda3\
lib\site
-packages (from tensorflow-intel==2.17.0->tensorflow) (0.2.0)
Requirement already satisfied: h5py>=3.10.0 in c:\users\divya\anaconda3\lib\
site-packag es (from tensorflow-intel==2.17.0->tensorflow) (3.12.1)
Requirement already satisfied: libclang>=13.0.0 in c:\users\divya\anaconda3\
lib\site-pa ckages (from tensorflow-intel==2.17.0->tensorflow) (18.1.1)
Requirement already satisfied: ml-dtypes<0.5.0,>=0.3.1 in c:\users\divya\
anaconda3\lib
\site-packages (from tensorflow-intel==2.17.0->tensorflow) (0.4.1)
Requirement already satisfied: opt-einsum>=2.3.2 in c:\users\divya\anaconda3\
lib\site-p ackages (from tensorflow-intel==2.17.0->tensorflow) (3.4.0)
Requirement already satisfied: packaging in c:\users\divya\anaconda3\lib\site-
packages (from tensorflow-intel==2.17.0->tensorflow) (23.1)
Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!
=4.21.4,!= 4.21.5,<5.0.0dev,>=3.20.3 in c:\users\divya\anaconda3\lib\site-
packages (from tensorflo w-intel==2.17.0->tensorflow) (4.25.5)
Requirement already satisfied: requests<3,>=2.21.0 in c:\users\divya\anaconda3\
lib\site
-packages (from tensorflow-intel==2.17.0->tensorflow) (2.31.0)
Requirement already satisfied: setuptools in c:\users\divya\anaconda3\lib\site-
packages (from tensorflow-intel==2.17.0->tensorflow) (68.0.0)
Requirement already satisfied: six>=1.12.0 in c:\users\divya\anaconda3\lib\
site-package s (from tensorflow-intel==2.17.0->tensorflow) (1.16.0)
Requirement already satisfied: termcolor>=1.1.0 in c:\users\divya\anaconda3\
lib\site-pa ckages (from tensorflow-intel==2.17.0->tensorflow) (2.5.0)
Requirement already satisfied: typing-extensions>=3.6.6 in c:\users\divya\
anaconda3\lib
\site-packages (from tensorflow-intel==2.17.0->tensorflow) (4.7.1)
Requirement already satisfied: wrapt>=1.11.0 in c:\users\divya\anaconda3\lib\
site-packa ges (from tensorflow-intel==2.17.0->tensorflow) (1.14.1)
Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\users\divya\anaconda3\
lib\site
-packages (from tensorflow-intel==2.17.0->tensorflow) (1.66.2)
Requirement already satisfied: tensorboard<2.18,>=2.17 in c:\users\divya\
anaconda3\lib
\site-packages (from tensorflow-intel==2.17.0->tensorflow) (2.17.1)
Requirement already satisfied: keras>=3.2.0 in c:\users\divya\anaconda3\lib\
site-packag es (from tensorflow-intel==2.17.0->tensorflow) (3.6.0)
Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in c:\
users\divya\a naconda3\lib\site-packages (from tensorflow-intel==2.17.0-
>tensorflow) (0.31.0)
Requirement already satisfied: numpy<2.0.0,>=1.23.5 in c:\users\divya\
anaconda3\lib\sit e-packages (from tensorflow-intel==2.17.0->tensorflow)
(1.24.3)
Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\users\divya\anaconda3\
lib\site- packages (from astunparse>=1.6.0->tensorflow-intel==2.17.0-
>tensorflow) (0.38.4)
Requirement already satisfied: rich in c:\users\divya\anaconda3\lib\site-
packages (from keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow) (13.9.2)
Requirement already satisfied: namex in c:\users\divya\anaconda3\lib\site-
packages (fro m keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow) (0.0.8)
Requirement already satisfied: optree in c:\users\divya\anaconda3\lib\site-
packages (fr om keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow) (0.13.0)
localhost:8888/notebooks/ 29/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Requirement already satisfied:Notebook
charset-normalizer<4,>=2 in c:\users\divya\
anaconda3\lib
\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.17.0->tensorflow)
(2.0.4) Requirement already satisfied: idna<4,>=2.5 in c:\users\divya\
anaconda3\lib\site-packag es (from requests<3,>=2.21.0->tensorflow-
intel==2.17.0->tensorflow) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in c:\users\divya\anaconda3\
lib\site- packages (from requests<3,>=2.21.0->tensorflow-intel==2.17.0-
>tensorflow) (1.26.16)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\divya\anaconda3\
lib\site- packages (from requests<3,>=2.21.0->tensorflow-intel==2.17.0-
>tensorflow) (2024.6.2)
Requirement already satisfied: markdown>=2.6.8 in c:\users\divya\anaconda3\lib\
site-pac kages (from tensorboard<2.18,>=2.17->tensorflow-intel==2.17.0-
>tensorflow) (3.4.1)
Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in c:\users\
divya

localhost:8888/notebooks/ 30/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
\anaconda3\lib\site-packages (from tensorboard<2.18,>=2.17->tensorflow-
intel==2.17.0->t ensorflow) (0.7.2)
Requirement already satisfied: werkzeug>=1.0.1 in c:\users\divya\anaconda3\lib\
site-pac kages (from tensorboard<2.18,>=2.17->tensorflow-intel==2.17.0-
>tensorflow) (2.2.3)
Requirement already satisfied: MarkupSafe>=2.1.1 in c:\users\divya\anaconda3\
lib\site-p ackages (from werkzeug>=1.0.1->tensorboard<2.18,>=2.17->tensorflow-
intel==2.17.0->tenso rflow) (2.1.1)
Requirement already satisfied: markdown-it-py>=2.2.0 in c:\users\divya\
anaconda3\lib\si te-packages (from rich->keras>=3.2.0->tensorflow-
intel==2.17.0->tensorflow) (2.2.0)
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in c:\users\divya\
anaconda3\lib
\site-packages (from rich->keras>=3.2.0->tensorflow-intel==2.17.0->tensorflow)
(2.15.1) Requirement already satisfied: mdurl~=0.1 in c:\users\divya\anaconda3\
lib\site-packages (from markdown-it-py>=2.2.0->rich->keras>=3.2.0->tensorflow-
intel==2.17.0->tensorflow) (0.1.0)

In [55]: import tensorflow as tf

# Create scalar tensor variables a and b

a = tf.constant(5) # Example scalar value for a
b = tf.constant(10) # Example scalar value for b

# Perform addition operation

result = tf.add(a, b)

# Display the result

print("Addition Result:", result.numpy())

Addition Result: 15

In [56]: import tensorflow as tf

# Create a variable for x and use the provided values

x = tf.constant([0, 5, 15, 25])

# Compute y = x * 10 + 500
y = x * 10 + 500

# Display the result

print("Computed y values:", y.numpy())

Computed y values: [500 550 650 750]

In [57]: # lab experiment 10

import tensorflow as tf

# Create a constant tensor for x

x = tf.constant([[12, 2, 0, -2], [14, 4, 1, 0]])

# Compute y = x * 10 + 1
y = x * 10 + 1

# Display the result

print("Computed y values:\n", y.numpy())

Computed y
values: [[121
21 1 -
19]
[141 41 11 1]]

localhost:8888/notebooks/ 31/2
ca2_advanced_python.ipynb
10/14/24, 7:10 ca2_advanced_python - Jupyter
PM Notebook
In [58]: import tensorflow as tf

# Input scalar values at runtime

tens1_value = float(input("Enter a scalar value for
tens1: ")) tens2_value = float(input("Enter a scalar
value for tens2: "))

# Create tensor variables for tens1 and tens2

tens1 =
tf.constant(tens1_value)
tens2 =
tf.constant(tens2_value)

# Perform multiplication
result = tf.multiply(tens1, tens2)

# Display the result

Enter a scalar value for tens1: 12
Enter a scalar value for tens2: 2
Multiplication Result: 24.0

In [ ]:

localhost:8888/notebooks/ 32/2
ca2_advanced_python.ipynb