WebScraping with Gen AI

During this session, we'll explore the following topics:

1️⃣ Basics of Web Scraping:
Understand the fundamental concepts and techniques of web scraping and its legal and ethical considerations.

2️⃣ Scraping with Gen AI:
Discover how Gen AI revolutionizes the web scraping landscape with real-world examples.

3️⃣ Jina Reader API:
Get acquainted with the Jina Reader API, a powerful tool for obtaining LLM-friendly input from URLs or web searches.

4️⃣ ScrapeGraphAI:
Dive into ScrapeGraphAI, a groundbreaking Python library that combines LLMs and direct graph logic for creating robust scraping pipelines.

Event Details:
🗓 Date: 22 June, Saturday
⏰ Time: 11:00 AM IST
🔗 Register now: https://www.buildfastwithai.com/events/web-scraping-with-gen-ai

Connect with Founder from IIT Delhi;
https://www.linkedin.com/in/satvik-paramkusham/

🟢 Let's start with Day 1 today

Let's learn Linear Regression in detail

Linear regression is a statistical method used to model the relationship between a dependent variable (target) and one or more independent variables (features). The goal is to find the linear equation that best predicts the target variable from the feature variables.

The equation of a simple linear regression model is:
\[ y = \beta_0 + \beta_1 x \]
Where:
- \( y) is the predicted value.
- \( \beta_0) is the y-intercept.
- \( \beta_1) is the slope of the line (coefficient).
- \( x) is the independent variable.

✅ Implementation

Let's consider an example using Python and its libraries.

✅ Example
Suppose we have a dataset with house prices and their corresponding size (in square feet).

# Import necessary libraries
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
import matplotlib.pyplot as plt

# Example data
data = {
    'Size': [1500, 1600, 1700, 1800, 1900, 2000, 2100, 2200, 2300, 2400],
    'Price': [300000, 320000, 340000, 360000, 380000, 400000, 420000, 440000, 460000, 480000]
}
df = pd.DataFrame(data)

# Independent variable (feature) and dependent variable (target)
X = df[['Size']]
y = df['Price']

# Splitting the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

# Creating and training the linear regression model
model = LinearRegression()
model.fit(X_train, y_train)

# Making predictions
y_pred = model.predict(X_test)

# Evaluating the model
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

print(f"Mean Squared Error: {mse}")
print(f"R-squared: {r2}")

# Plotting the results
plt.scatter(X, y, color='blue')  # Original data points
plt.plot(X_test, y_pred, color='red', linewidth=2)  # Regression line
plt.xlabel('Size (sq ft)')
plt.ylabel('Price ($)')
plt.title('Linear Regression: House Prices vs Size')
plt.show()

✅ Explanation of the Code

1. Libraries: We import necessary libraries like numpy, pandas, sklearn, and matplotlib.
2. Data Preparation: We create a DataFrame containing the size and price of houses.
3. Feature and Target: We separate the feature (Size) and the target (Price).
4. Train-Test Split: We split the data into training and testing sets.
5. Model Training: We create a LinearRegression model and train it using the training data.
6. Predictions: We use the trained model to predict house prices for the test set.
7. Evaluation: We evaluate the model using Mean Squared Error (MSE) and R-squared (R²) metrics.
8. Visualization: We plot the original data points and the regression line to visualize the model's performance.

✅ Evaluation Metrics

- Mean Squared Error (MSE): Measures the average squared difference between the actual and predicted values. Lower values indicate better performance.
- R-squared (R²): Represents the proportion of the variance in the dependent variable that is predictable from the independent variable(s). Values closer to 1 indicate a better fit.

👇 BEST DATA SCIENCE CHANNELS ON TELEGRAM 👇

https://t.me/addlist/8_rRW2scgfRhOTc0

🌟 Modded-NanoGPT - allows you to achieve GPT-2 quality (124M) when training on only 5B tokens

Modded-NanoGPT is a modification of the GPT-2 training code from Andrei Karpathy.

Modded-NanoGPT allows:
- train 2 times more efficiently (requires only 5B tokens instead of 10B to achieve the same accuracy)
- has simpler code (446 lines instead of 858)

🖥 GitHub

👇 BEST DATA SCIENCE CHANNELS ON TELEGRAM 👇

https://t.me/addlist/8_rRW2scgfRhOTc0

¡Hola! 👋
AmigoChat - AI GPT bot. Best friend and assistant:

✅ use GPT 4 Omni
✅ generate images
✅ get ideas and hashtags for social media
✅ write SEO texts
✅ rewrite and summarize longreads
✅ choose a promotion plan
✅ chat and ask questions

Everything is FREE because amigos don't take dineros for help! 🤠
👉 https://t.me/Amigoo_Chat_Bot

👍 ExVideo is a tuning technique to improve the ability of models to generate video

ExVideo allows a model to generate 5 times more frames, while requiring only 1.5k GPU training hours on a dataset of 40k videos.

In particular, ExVideo was used to improve the Stable Video Diffusion model to generate long videos up to 128 frames.
The code, article and model are at the links below.

🟡 ExVideo page
🖥 GitHub
🟡 Hugging Face
🟡 Arxiv

👇 BEST DATA SCIENCE CHANNELS ON TELEGRAM 👇

https://t.me/addlist/8_rRW2scgfRhOTc0

🆒 EAGLE is a method that allows you to generate LLM responses faster

Is it possible to generate LLM response on two RTX 3060s faster than on A100 (which is 16+ times more expensive)?
Yes, it is possible with EAGLE (Extrapolation Algorithm for Greater Language-model Efficiency) and the accuracy of the responses is preserved.

EAGLE allows you to extrapolate the context feature vectors of the second top layer of the LLM, which greatly improves the generation efficiency.

EAGLE is 2x faster than Lookahead (13B), and 1.6x faster than Medusa (13B).
And yes, EAGLE can be combined with other acceleration techniques like vLLM, DeepSpeed, Mamba, FlashAttention, quantization and hardware optimization.

🤗 Hugging Face
💻 GitHub