Merge pull request #1475 from ananas304/main

Projects under the 'Algorithms and Deep Learning Models' directory are missing README files are now added

Author: sanjay-kv

Algorithms and Deep Learning Models/Boxoffice/Boxoffice.ipynb

@@ -6,6 +6,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Import necessary libraries\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "import matplotlib.pyplot as plt\n",
@@ -22,7 +23,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df=pd.read_csv(\"D:/Documents/Data Sets/film.csv\")"
+    "# Load the dataset\n",
+    "df=pd.read_csv(\"D:/Documents/Data Sets/movie_dataset.csv\")"
    ]
   },
   {
@@ -31,6 +33,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Display the first 5 rows of the dataset\n",
     "df.head(5)"
    ]
   },
@@ -40,6 +43,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Get the shape of the dataset\n",
     "df.shape"
    ]
   },
@@ -49,6 +53,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Check for missing values in the dataset\n",
     "df.isnull().sum()"
    ]
   },
@@ -58,6 +63,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Drop rows with missing values\n",
     "df.dropna(inplace=True)"
    ]
   },
@@ -67,6 +73,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Verify that there are no more missing values\n",
     "df.isnull().sum()"
    ]
   },
@@ -76,6 +83,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Display information about the dataset\n",
     "df.info()"
    ]
   },
@@ -85,7 +93,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "cor=df['Budget'].corr(df['Revenue'])\n",
+    "# Calculate and display correlation between budget and revenue\n",
+    "cor=df['budget'].corr(df['revenue'])\n",
     "cor"
    ]
   },
@@ -95,18 +104,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Encode categorical variables using Label Encoding\n",
     "lr=preprocessing.LabelEncoder()\n",
-    "df['Title']=lr.fit_transform(df['Title'])\n",
-    "df['Original Title']=lr.fit_transform(df['Original Title'])\n",
-    "df['Original Language']=lr.fit_transform(df['Original Language'])\n",
-    "df['Status']=lr.fit_transform(df['Status'])\n",
-    "df['Spoken Languages']=lr.fit_transform(df['Spoken Languages'])\n",
-    "df['Production Countries']=lr.fit_transform(df['Production Countries'])\n",
-    "df['Production Companies']=lr.fit_transform(df['Production Companies'])\n",
-    "df['Genres']=lr.fit_transform(df['Genres'])\n",
-    "df['Overview']=lr.fit_transform(df['Overview'])\n",
-    "df['Release Date']=lr.fit_transform(df['Release Date'])\n",
-    "df['Adult']=lr.fit_transform(df['Adult'])\n"
+    "df['title']=lr.fit_transform(df['title'])\n",
+    "df['original_title']=lr.fit_transform(df['original_title'])\n",
+    "df['original_language']=lr.fit_transform(df['original_language'])\n",
+    "df['status']=lr.fit_transform(df['status'])\n",
+    "df['spoken_languages']=lr.fit_transform(df['spoken_languages'])\n",
+    "df['production_countries']=lr.fit_transform(df['production_countries'])\n",
+    "df['production_companies']=lr.fit_transform(df['production_companies'])\n",
+    "df['genres']=lr.fit_transform(df['genres'])\n",
+    "df['overview']=lr.fit_transform(df['overview'])\n",
+    "df['release_date']=lr.fit_transform(df['release_date'])\n"
    ]
   },
   {
@@ -115,6 +124,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Display information about the dataset after encoding\n",
     "df.info()"
    ]
   },
@@ -124,7 +134,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sns.heatmap(data=df)"
+    "# Create and display a heatmap of feature correlations\n",
+    "correlation_matrix = df.select_dtypes(include=[np.number]).corr()\n",
+    "plt.figure(figsize=(14, 10))\n",
+    "sns.heatmap(correlation_matrix, annot=True, fmt='.2f', cmap='coolwarm', square=True, cbar_kws={\"shrink\": .8})\n",
+    "plt.title('Heatmap of Feature Correlations', fontsize=20)\n",
+    "plt.xticks(rotation=45, ha='right')\n",
+    "plt.yticks(rotation=0)\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
    ]
   },
   {
@@ -133,8 +151,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "X=df[['Budget','Popularity','Runtime']]\n",
-    "Y=df['Revenue']\n"
+    "# Define features and target variable for the model\n",
+    "X=df[['budget','popularity','runtime']]\n",
+    "Y=df['revenue']\n"
    ]
   },
   {
@@ -143,6 +162,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Split the data into training and testing sets\n",
     "x_train, x_test, y_train, y_test=train_test_split(X,Y, test_size=0.4)"
    ]
   },
@@ -152,6 +172,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Create a Linear Regression model\n",
     "lr=LinearRegression()"
    ]
   },
@@ -161,6 +182,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Fit the model to the training data\n",
     "lr.fit(x_train, y_train)"
    ]
   },
@@ -170,6 +192,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Make predictions on the testing set\n",
     "pred=lr.predict(x_test)"
    ]
   },
@@ -179,6 +202,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Evaluate the model using Mean Absolute Error\n",
     "print(metrics.mean_absolute_error(y_test, pred))"
    ]
   }

Algorithms and Deep Learning Models/Boxoffice/README.md

@@ -0,0 +1,49 @@
+# Movie Revenue Prediction
+This project aims to predict movie revenue based on various features such as budget, popularity, and runtime using a linear regression model.
+
+## Table of Contents
+- [Installation](#installation)
+- [Dataset](#dataset)
+- [Usage](#usage)
+- [Results](#results)
+
+## Installation
+
+To run this project, you'll need to have Python installed along with the following libraries:
+```requirements.txt
+NumPy
+Pandas
+Matplotlib
+Seaborn
+Scikit-learn
+```
+You can install the necessary libraries using pip:
+
+```bash
+pip install -r requirements.txt
+```
+
+## Dataset
+
+The dataset used in this project is `movie_dataset.csv`, which contains information about various movies, including their budget, revenue, popularity, runtime, and more.
+
+## Usage
+
+1. Clone the repository:
+
+```bash
+git clone <your-repo-url>
+cd <your-repo-directory>
+```
+
+2. Open the Jupyter Notebook:
+
+```bash
+jupyter notebook
+```
+
+3. Run the notebook cells sequentially to load the dataset, preprocess it, and train the linear regression model to make predictions on movie revenue.
+
+## Results
+
+After running the model, you will receive the Mean Absolute Error (MAE) as an evaluation metric to assess the prediction accuracy.

Algorithms and Deep Learning Models/Boxoffice/movie_dataset.csv

@@ -0,0 +1,5 @@
+numpy
+pandas
+matplotlib
+seaborn
+scikit-learn

Algorithms and Deep Learning Models/Boxoffice/reqiurements.md

@@ -0,0 +1,70 @@
+# Erasing Clouds from Satellite Imagery
+
+This project focuses on developing a deep learning model to remove clouds from satellite imagery. Clouds obstruct critical information in satellite images, making it difficult to analyze geographic, agricultural, and environmental features. By building a model that can effectively "erase" clouds, this project aims to provide clearer, more accurate satellite images for better analysis and decision-making.
+
+## Overview
+
+Satellite images are essential for various industries such as agriculture, weather forecasting, environmental monitoring, and more. However, clouds often cover parts of these images, obstructing the view of the Earth's surface. This project provides a solution by processing satellite images and removing clouds, resulting in a clearer image of the terrain below.
+
+The process involves training a deep learning model on paired images — one set of images containing clouds and another set of the same location without clouds. Through multiple training iterations, the model learns how to predict and generate cloud-free images, enhancing the usability of satellite imagery.
+
+## Features
+
+- **Cloud Removal from Satellite Images**: The model removes cloud cover from satellite images to reveal the underlying terrain.
+- **Loss Visualization**: Training progress is visualized using loss plots for both the generator and discriminator components.
+- **Customizable Design**: The model's training parameters can be adjusted to enhance performance based on specific datasets.
+- **Visual Representation**: The model provides visual feedback on training progress, with clear indications of where improvements are being made.
+
+## Setup
+
+To run this project locally, follow these steps:
+
+### Prerequisites
+
+- Python 3.x
+- Required libraries:
+  - `matplotlib`
+  - `numpy`
+  - `torch`
+  - `PIL`
+
+Install the required libraries using pip:
+
+```bash
+pip install matplotlib numpy torch pillow
+```
+
+### Clone the Repository
+
+Clone this repository to your local machine:
+
+```bash
+git clone <repository-url>
+cd <repository-directory>
+```
+
+### Running the Project
+
+1. Place the training and validation datasets in the appropriate folder (dataset structure to be defined based on your use case).
+3. Losses for both the generator and discriminator are plotted and saved as images after training.
+
+### Visualizing Losses
+
+The loss curves for the training process can be visualized using `matplotlib`:
+
+```python
+plt.show()
+```
+
+You can find the generated loss plots in the project directory as `Loss.jpg`.
+
+## Usage
+
+After training, the model can be used to process new satellite images and remove cloud cover:
+
+```python
+python inference.py --input_image <path_to_cloudy_image>
+```
+
+This will output a cloud-free image that can be used for further analysis.
+

Algorithms and Deep Learning Models/Erasing Clouds from Satellite Imagery/README.md

@@ -0,0 +1,44 @@
+# QR Code Scanner
+
+This project is a simple QR code scanner that uses OpenCV to capture video from a webcam and detects QR codes in real-time. Once a QR code is detected, the URL or data encoded in the QR code will automatically be opened in your default web browser.
+
+## Features
+- Real-time QR code detection using a webcam.
+- Automatically opens the decoded URL in the default web browser.
+- Exits the application after a QR code is successfully scanned and opened.
+
+## Requirements
+
+Before running the project, ensure you have the following installed:
+
+- Python 3.x
+- OpenCV (`cv2`)
+- A webcam (integrated or external)
+
+### Python Dependencies
+You can install the necessary dependencies using the following commands:
+
+```bash
+pip install opencv-python
+```
+
+## How to Run the Project
+1. Clone or download the project to your local machine.
+2. Navigate to the project directory.
+3. Ensure you have a working webcam connected.
+4. Run the Python script:
+```bash
+python qr_scan.py
+```
+The webcam will start, and as soon as a QR code is detected, its URL will be opened in your default web browser.
+
+## Screenshots
+- Here is an example of the QR code scanner in action:
+    1. **Camera Window Capturing QR Code:**
+   ![QR Code Scanner Capturing](https://github.com/ananas304/machine-learning-repos/blob/main/Algorithms%20and%20Deep%20Learning%20Models/QR-Scanner/QR_Scanne-qr%20code%20image%20capture.png)
+
+   In this screenshot, the camera window is open, and it's capturing a QR code in real-time.
+
+## Notes
+- The application will exit automatically after a QR code is detected and the link is opened.
+- Press the q key to exit the scanner manually at any time.

Algorithms and Deep Learning Models/QR-Scanner/QR_Scanne-qr code image capture.png

@@ -1,5 +1,4 @@
 import cv2
-from pyzbar.pyzbar import decode
 import webbrowser
 
 # Function to open web browser with the decoded QR code link
@@ -11,26 +10,25 @@ def open_link_once(url):
 cam.set(3, 640)  # Width
 cam.set(4, 480)  # Height
 
+# Initialize the QRCode detector
+detector = cv2.QRCodeDetector()
+
 while True:
     success, frame = cam.read()
 
-    # Decode QR codes
-    for barcode in decode(frame):
-        # Extract barcode data
-        qr_data = barcode.data.decode('utf-8')
-        print(f"QR Code data: {qr_data}")
+    # Detect and decode the QR code
+    data, bbox, _ = detector.detectAndDecode(frame)
+
+    if data:
+        print(f"QR Code data: {data}")
 
         # Open the URL in a web browser only once
-        open_link_once(qr_data)
-        break  # Break out of the for loop after opening the link
+        open_link_once(data)
+        break  # Break out of the loop after opening the link
 
     # Display the camera frame
     cv2.imshow('QR Scanner', frame)
 
-    # Check if link has been opened and break out of the main loop
-    if 'qr_data' in locals():
-        break
-
     # Wait for key press and break loop if 'q' is pressed
     if cv2.waitKey(1) & 0xFF == ord('q'):
         break

Algorithms and Deep Learning Models/QR-Scanner/README.md

@@ -0,0 +1 @@
+opencv-python==4.10.0.84