Scribd
Upload
10 views5 pages

IDML Lab Programs

Uploaded by

Priya Yannam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
10 views5 pages

IDML Lab Programs

Uploaded by

Priya Yannam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

1.

Cleaning Data in Pandas and Visualizing with Matplotlib

# Import necessary libraries

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

# Create a sample DataFrame with missing values

data = {

'Name': ['John', 'Anna', 'Peter', 'Linda', np.nan],

'Age': [28, 22, np.nan, 32, 40],

'Score': [85, 90, np.nan, 78, 95]

df = pd.DataFrame(data)

# Data Cleaning: Remove rows with missing values

df_cleaned = df.dropna()

# Visualize the cleaned data using Matplotlib

plt.figure(figsize=(6, 4))

df_cleaned.plot(kind='bar', x='Name', y='Score', legend=False)

plt.title('Scores of Students')

plt.xlabel('Student Name')

plt.ylabel('Score')

plt.show()

2. Analyzing Data in Pandas


# Import pandas and numpy libraries

import pandas as pd

import numpy as np

# Create a sample DataFrame

data = {

'Name': ['John', 'Anna', 'Peter', 'Linda', np.nan],

'Age': [28, 22, np.nan, 32, 40],

'Score': [85, 90, np.nan, 78, 95]

df = pd.DataFrame(data)

# Descriptive statistics

print("Descriptive statistics:\n", df.describe())

# Calculate mean, median, and standard deviation

mean_age = df['Age'].mean()

median_score = df['Score'].median()

std_age = df['Age'].std()

print("\nMean Age:", mean_age)

print("Median Score:", median_score)

print("Standard Deviation of Age:", std_age)

# Grouping by 'Name' and aggregating 'Score'

grouped_scores = df.groupby('Name')['Score'].mean()
print("\nGrouped Scores (by Name):\n", grouped_scores)

# Filter rows where 'Age' is greater than 30

filtered_df = df[df['Age'] > 30]

print("\nFiltered DataFrame (Age > 30):\n", filtered_df)

3. Creating a Simple Pandas DataFrame

# Import pandas library

import pandas as pd

# Create a simple DataFrame

data = {

'Name': ['Alice', 'Bob', 'Charlie'],

'Age': [25, 30, 35],

'Score': [88, 92, 85]

df = pd.DataFrame(data)

# Display the DataFrame

print(df)

4. Creating a Filter Array for Even Elements

# Import numpy library

import numpy as np

# Original array

arr = np.array([1, 2, 3, 4, 5, 6, 7, 8])


# Filter even elements

even_elements = arr[arr % 2 == 0]

# Display the even elements

print("Even elements in the array:", even_elements)

5. Normal Distribution and Poisson Distribution

# Import numpy and matplotlib libraries

import numpy as np

import matplotlib.pyplot as plt

# Generate a normal distribution

mean, std_dev = 0, 1 # Mean and standard deviation

normal_data = np.random.normal(mean, std_dev, 1000)

# Plot normal distribution

plt.figure(figsize=(6, 4))

plt.hist(normal_data, bins=30, density=True)

plt.title('Normal Distribution')

plt.xlabel('Value')

plt.ylabel('Density')

plt.show()

# Generate a Poisson distribution

lambda_val = 5 # Rate of occurrence


poisson_data = np.random.poisson(lambda_val, 1000)

# Plot Poisson distribution

plt.figure(figsize=(6, 4))

plt.hist(poisson_data, bins=15, density=True)

plt.title('Poisson Distribution')

plt.xlabel('Occurrences')

plt.ylabel('Probability')

plt.show()

6. Convert 1D Array to 3D Array

# Import numpy library

import numpy as np

# 1D array with 8 elements

arr_1d = np.array([1, 2, 3, 4, 5, 6, 7, 8])

# Reshape to a 3D array with shape 2x2x2

arr_3d = arr_1d.reshape(2, 2, 2)

# Display the 3D array

print("3D Array:\n", arr_3d)

You might also like