Roadmap

Weak 1: Python basics

Day 1:

Libreries Understanding

Day 2:

Data Loading and Its manipulation

Day 3:

Graphs and Plots

Day 4:

Machine Learning Basics

Day 5:

Machine Learning Algorithms

Weak 2: Machine Learning Tasks

Day 1:

Linear Regression

Day 2:

Classification

Day 3:

Clustering

Day 4:

Deep Learning Basics

Day 5:

Neural Networks, Tensorflow and Keras

Day 1:

Deep Learning Algorithms

Day 2:

Convolutional Neural Networks

Day 3:

Recuurent Neural Networks

Day 4:

NLP

Day 5:

GANS

Week 4: Deep Learning Tasks

Python Basics Pandas, Numpy, Matplotlib

Machine Learning Libreries

Regression

Classification

Deep Learning

Python has emerged as the premier language for machine learning (ML), playing a pivotal role in both
academic research and industry applications. Its popularity stems from a combination of ease of use,
extensive libraries, strong community support, and flexibility. Here, we delve into the reasons why
Python is the language of choice for machine learning, highlighting its key features and benefits.

1. Ease of Learning and Use

Python's syntax is intuitive and readable, making it accessible to both beginners and experienced
developers. Its clean and straightforward structure allows users to focus on understanding machine
learning concepts rather than grappling with complex language syntax. This ease of learning accelerates
the onboarding process for new developers and facilitates rapid prototyping and experimentation, which
are crucial in the fast-paced field of machine learning.

2. Extensive Libraries and Frameworks

Python boasts a rich ecosystem of libraries and frameworks that significantly streamline the
development of machine learning models:

NumPy: Essential for numerical computations,

Pandas: Provides data structures and data analysis tools, making it easier to handle and preprocess data.

Matplotlib and Seaborn: Powerful libraries for data visualization, allowing for the creation of informative
and aesthetically pleasing plots and graphs.

Scikit-learn: A comprehensive library for traditional machine learning algorithms, including tools for
model selection, preprocessing, and evaluation.

TensorFlow and Keras: Popular libraries for deep learning, offering flexible and efficient tools for building
neural networks.

PyTorch: Another leading deep learning library known for its dynamic computation graph and ease of
use, particularly favored in research.

These libraries and frameworks offer pre-built modules and functions, reducing the need for writing
boilerplate code and enabling developers to focus on refining their models and algorithms.

NUMPY:

Basic Examples of NumPy Library

NumPy (Numerical Python) is a powerful library for numerical computing in Python. It provides support
for arrays, matrices, and a wide range of mathematical functions. Here are some basic examples to help
you get started with NumPy.

1. Installing NumPy

First, ensure you have NumPy installed. You can install it using pip:

sh

Copy code

pip install numpy

2. Importing NumPy

To use NumPy, you need to import it. It is common to import it with the alias np:

python

Copy code

import numpy as np

3. Creating Arrays

1D Array:

python

Copy code

import numpy as np

# Creating a 1D array

array_1d = np.array([1, 2, 3, 4, 5])

print("1D Array:", array_1d)

2D Array:
python

Copy code

# Creating a 2D array (matrix)

array_2d = np.array([[1, 2, 3], [4, 5, 6]])

print("2D Array:\n", array_2d)

Array of Zeros:

python

Copy code

# Creating an array of zeros

zeros_array = np.zeros((3, 3))

print("Zeros Array:\n", zeros_array)

Array of Ones:

python

Copy code

# Creating an array of ones

ones_array = np.ones((2, 4))

print("Ones Array:\n", ones_array)

Array with a Range of Values:

python

Copy code

# Creating an array with a range of values

print("Range Array:", range_array)

Array of Linearly Spaced Values:

python

Copy code

# Creating an array of linearly spaced values

linspace_array = np.linspace(0, 1, 5) # 5 values between 0 and 1

print("Linearly Spaced Array:", linspace_array)

4. Basic Operations

Element-wise Operations:

python

Copy code

# Adding, subtracting, multiplying, and dividing arrays

a = np.array([1, 2, 3])

b = np.array([4, 5, 6])

print("Addition:", a + b)

print("Subtraction:", a - b)

print("Multiplication:", a * b)

print("Division:", a / b)

Universal Functions (ufuncs):

python
Copy code

# Applying mathematical functions

a = np.array([1, 2, 3, 4, 5])

print("Square Root:", np.sqrt(a))

print("Exponential:", np.exp(a))

print("Sine:", np.sin(a))

5. Array Indexing and Slicing

Indexing:

python

Copy code

# Accessing elements

a = np.array([1, 2, 3, 4, 5])

print("First Element:", a[0])

print("Last Element:", a[-1])

Slicing:

python

Copy code

# Slicing arrays

b = np.array([10, 20, 30, 40, 50])

print("Elements from index 1 to 3:", b[1:4])

print("Elements from start to index 2:", b[:3])

print("Elements from index 3 to end:", b[3:])

python

Copy code

# Accessing elements and subarrays in 2D arrays

matrix = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])

print("Element at (0, 0):", matrix[0, 0])

print("First row:", matrix[0, :])

print("Second column:", matrix[:, 1])

print("Subarray:\n", matrix[1:, 1:])

6. Reshaping Arrays

Reshape:

python

Copy code

# Reshaping arrays

a = np.arange(1, 10)

reshaped_array = a.reshape((3, 3))

print("Reshaped Array:\n", reshaped_array)

7. Aggregations and Statistics

Sum, Mean, and Standard Deviation:

python

Copy code

# Aggregation functions
a = np.array([1, 2, 3, 4, 5])

print("Sum:", np.sum(a))

print("Mean:", np.mean(a))

print("Standard Deviation:", np.std(a))

Max and Min:

python

Copy code

# Finding the maximum and minimum values

b = np.array([10, 20, 30, 40, 50])

print("Maximum Value:", np.max(b))

print("Minimum Value:", np.min(b))

These examples cover the basics of NumPy, providing a foundation for more advanced numerical
computations and data manipulation. NumPy's efficiency and functionality make it a crucial tool for
scientific computing and machine learning in Python.

Basic Example of Matplotlib

Matplotlib is a comprehensive library for creating static, animated, and interactive visualizations in
Python. It is particularly useful for generating plots, histograms, bar charts, scatter plots, and much
more. Here’s a basic guide to get you started with Matplotlib.

1. Installing Matplotlib

First, ensure you have Matplotlib installed. You can install it using pip:

sh
Copy code

pip install matplotlib

2. Importing Matplotlib

To use Matplotlib, you need to import it. It is common to import the pyplot module as plt:

python

Copy code

import matplotlib.pyplot as plt

3. Creating a Simple Line Plot

A line plot is the simplest type of plot in Matplotlib. Here's how to create one:

python

Copy code

import matplotlib.pyplot as plt

# Data

x = [1, 2, 3, 4, 5]

y = [2, 3, 5, 7, 11]

# Create the plot

plt.plot(x, y)

# Add titles and labels

plt.title('Simple Line Plot')

plt.xlabel('X-axis')
plt.ylabel('Y-axis')

# Show the plot

plt.show()

4. Creating a Scatter Plot

A scatter plot is useful for displaying the relationship between two numerical variables.

python

Copy code

import matplotlib.pyplot as plt

# Data

x = [1, 2, 3, 4, 5]

y = [2, 3, 5, 7, 11]

# Create the scatter plot

plt.scatter(x, y)

# Add titles and labels

plt.title('Simple Scatter Plot')

plt.xlabel('X-axis')

plt.ylabel('Y-axis')

# Show the plot

plt.show()
5. Creating a Bar Plot

A bar plot is used to display values for different categorical data.

python

Copy code

import matplotlib.pyplot as plt

# Data

categories = ['A', 'B', 'C', 'D', 'E']

values = [4, 7, 1, 8, 5]

# Create the bar plot

plt.bar(categories, values)

# Add titles and labels

plt.title('Simple Bar Plot')

plt.xlabel('Categories')

plt.ylabel('Values')

# Show the plot

plt.show()

6. Creating a Histogram

A histogram is used to display the distribution of a dataset.

python
Copy code

import matplotlib.pyplot as plt

import numpy as np

# Data

data = np.random.randn(1000)

# Create the histogram

plt.hist(data, bins=30)

# Add titles and labels

plt.title('Simple Histogram')

plt.xlabel('Value')

plt.ylabel('Frequency')

# Show the plot

plt.show()

7. Creating a Pie Chart

A pie chart is used to display proportions of a whole.

python

Copy code

import matplotlib.pyplot as plt

# Data
labels = ['A', 'B', 'C', 'D']

sizes = [15, 30, 45, 10]

# Create the pie chart

plt.pie(sizes, labels=labels, autopct='%1.1f%%')

# Add a title

plt.title('Simple Pie Chart')

# Show the plot

plt.show()

8. Adding Customizations

Matplotlib allows extensive customization to enhance the readability and aesthetics of the plots.

Changing Line Styles and Colors:

python

Copy code

plt.plot(x, y, linestyle='--', color='r', marker='o') # Dashed red line with circle markers

Adding Grid:

python

Copy code

plt.grid(True)

Setting Axis Limits:

Copy code

plt.xlim(0, 6)

plt.ylim(0, 12)

Adding a Legend:

python

Copy code

plt.plot(x, y, label='Prime Numbers')

plt.legend()

Saving the Plot:

You can save your plots to a file using savefig:

python

Copy code

plt.savefig('plot.png')

Complete Example

Here’s a complete example combining several elements:

python

Copy code

import matplotlib.pyplot as plt

import numpy as np
# Data

x = np.linspace(0, 10, 100)

y = np.sin(x)

# Create the plot

plt.plot(x, y, label='Sine Wave', color='b', linestyle='--')

# Customize the plot

plt.title('Sine Wave Example')

plt.xlabel('X-axis')

plt.ylabel('Y-axis')

plt.grid(True)

plt.legend()

# Save the plot

plt.savefig('sine_wave.png')

# Show the plot

plt.show()

This should give you a solid foundation for creating and customizing basic plots using Matplotlib. The
library’s extensive documentation and tutorials can further help you explore more advanced features
and customizations.

Pandas is a powerful and flexible data analysis and manipulation library for Python. It provides data
structures like Series and DataFrame, which are essential for handling structured data efficiently. Here’s
an overview of the basics of Pandas to get you started.
1. Installing Pandas

First, ensure you have Pandas installed. You can install it using pip:

sh

Copy code

pip install pandas

2. Importing Pandas

To use Pandas, you need to import it, commonly using the alias pd:

python

Copy code

import pandas as pd

3. Pandas Data Structures

Pandas has two primary data structures: Series and DataFrame.

Series

A Series is a one-dimensional labeled array capable of holding any data type.

python

Copy code

import pandas as pd

# Creating a Series

s = pd.Series([1, 3, 5, 7, 9])
print(s)

DataFrame

A DataFrame is a two-dimensional labeled data structure with columns of potentially different types.

python

Copy code

import pandas as pd

# Creating a DataFrame

data = {

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

'Age': [24, 27, 22, 32],

'City': ['New York', 'Los Angeles', 'Chicago', 'Houston']

df = pd.DataFrame(data)

print(df)

4. Reading Data

Pandas can read data from various file formats such as CSV, Excel, SQL databases, and more.

python

Copy code

# Reading data from a CSV file

df = pd.read_csv('data.csv')

print(df)

5. Basic Operations
Viewing Data:

python

Copy code

# Display the first few rows

print(df.head())

# Display the last few rows

print(df.tail())

Getting Basic Information:

python

Copy code

# Summary statistics

print(df.describe())

# DataFrame information

print(df.info())

Selecting Data:

python

Copy code

# Selecting a column

print(df['Name'])
# Selecting multiple columns

print(df[['Name', 'Age']])

# Selecting rows by index

print(df.iloc[1]) # Second row (index starts at 0)

print(df.iloc[1:3]) # Second and third rows

# Selecting rows by condition

print(df[df['Age'] > 25])

Adding a New Column:

python

Copy code

# Adding a new column

df['Salary'] = [50000, 60000, 45000, 80000]

print(df)

Modifying a Column:

python

Copy code

# Modifying a column

df['Age'] = df['Age'] + 1

print(df)

Dropping a Column:
python

Copy code

# Dropping a column

df = df.drop(columns=['Salary'])

print(df)

6. Handling Missing Data

Detecting Missing Data:

python

Copy code

# Checking for missing values

print(df.isnull())

print(df.isnull().sum())

Filling Missing Data:

python

Copy code

# Filling missing values with a specified value

df['Age'] = df['Age'].fillna(0)

print(df)

Dropping Missing Data:

python

Copy code

# Dropping rows with missing values

print(df)

7. Grouping and Aggregating Data

Grouping Data:

python

Copy code

# Grouping by a column and calculating the mean

grouped = df.groupby('City').mean()

print(grouped)

Aggregating Data:

python

Copy code

# Aggregating data with different functions

agg = df.groupby('City').agg({'Age': 'mean', 'Salary': 'sum'})

print(agg)

8. Merging and Joining DataFrames

Merging DataFrames:

python

Copy code

# Creating two DataFrames

df1 = pd.DataFrame({'Key': ['A', 'B', 'C'], 'Value1': [1, 2, 3]})

df2 = pd.DataFrame({'Key': ['A', 'B', 'D'], 'Value2': [4, 5, 6]})

merged_df = pd.merge(df1, df2, on='Key', how='inner')

print(merged_df)

Joining DataFrames:

python

Copy code

# Setting the index for join operation

df1.set_index('Key', inplace=True)

df2.set_index('Key', inplace=True)

# Joining DataFrames

joined_df = df1.join(df2, how='outer')

print(joined_df)

9. Saving Data

To CSV:

python

Copy code

# Saving DataFrame to a CSV file

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

To Excel:

python
Copy code

# Saving DataFrame to an Excel file

df.to_excel('output.xlsx', index=False)

Conclusion

Pandas is an essential tool for data analysis and manipulation in Python. It provides powerful, flexible
data structures that make it easy to work with structured data. This basic overview should give you a
good starting point for using Pandas in your data projects

Introduction to Scikit-learn

Scikit-learn is a popular open-source machine learning library for Python. It provides simple and efficient
tools for data mining and data analysis, built on NumPy, SciPy, and Matplotlib. Scikit-learn offers a wide
range of supervised and unsupervised learning algorithms for classification, regression, clustering,
dimensionality reduction, and more. Here’s a basic overview of Scikit-learn to help you get started.

Key Features:

Simple and Consistent API: Scikit-learn provides a consistent interface for various machine learning
algorithms, making it easy to experiment with different models.

Wide Range of Algorithms: It includes implementations of many popular machine learning algorithms,
including support vector machines (SVM), random forests, k-nearest neighbors (KNN), decision trees,
and more.

Efficient and Optimized: Scikit-learn is optimized for performance and scalability, making it suitable for
both small and large datasets.

Built-in Datasets: It comes with several built-in datasets for practice and experimentation, allowing users
to get started quickly without the need for external data sources.
Model Evaluation: Scikit-learn provides tools for evaluating model performance through metrics such as
accuracy, precision, recall, F1-score, and area under the curve (AUC).

Data Preprocessing: It offers a range of preprocessing techniques for scaling, normalization, imputation,
feature extraction, and feature selection.

Integration with Other Libraries: Scikit-learn integrates seamlessly with other Python libraries such as
NumPy, Pandas, and Matplotlib, enabling a smooth workflow for data analysis and visualization.

Basic Usage:

1. Importing Scikit-learn:

python

Copy code

import sklearn

2. Loading Datasets:

Scikit-learn provides built-in datasets that can be loaded using the load_* functions.

python

Copy code

from sklearn.datasets import load_iris

# Load the Iris dataset

iris = load_iris()

# Accessing features and target

X = iris.data # Features
y = iris.target # Target

3. Splitting Data:

It is common to split the dataset into training and testing sets for model evaluation.

python

Copy code

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

4. Creating and Training Models:

Instantiate the desired model and fit it to the training data.

python

Copy code

from sklearn.linear_model import LogisticRegression

# Create the model

model = LogisticRegression()

# Train the model

model.fit(X_train, y_train)

5. Making Predictions:

Use the trained model to make predictions on new data.

python
Copy code

# Predictions on the test set

y_pred = model.predict(X_test)

6. Evaluating Model Performance:

Evaluate the model's performance using appropriate metrics.

python

Copy code

from sklearn.metrics import accuracy_score

accuracy = accuracy_score(y_test, y_pred)

print("Accuracy:", accuracy)