Internship completed

PADALA AKHIL NANDU YADAV/Readme.md.txt

@@ -0,0 +1,17 @@
+Advance Level
+
+Task 1 :Image Converter:
+
+Where the program that accepts images in multiple formats that may be in JPEG, PNG, BMP, GIF and converts them into a desired format using Python Imaging Library (PIL) that may be any of the formats mentioned.
+
+Task 2:Data Analysis with Pandas:
+
+In the program on loading the "Iris" dataset from Seaborn and analyzing it using Pandas and performed exploratory data analysis, cleaning, aggregation, visualizations, and correlation calculations. The output of the program will consits of calculations , graph which will be more understanding to users.
+
+Task 3:Linear Regression with Scikit-learn:
+
+Completed a program by applying linear regression to predict house prices from the Boston housing dataset using scikit-learn and compared train and test scores and plot residuals.
+
+Task 4:Image Compression:
+
+Developed a Python program for compressing images while maintaining quality by exploring compression techniques like RLE and DCT and allowing users to adjust compression quality, support various image formats, and provide output options. Optionally, include a user interface.

PADALA AKHIL NANDU YADAV/Task1.py

@@ -0,0 +1,33 @@
+from PIL import Image
+import os
+
+def convert_image(input_path, output_path, output_format):
+    try:
+        # Open the image
+        with Image.open(input_path) as img:
+            # Convert and save the image to the desired format
+            img.save(output_path, format=output_format)
+            print(f"Image converted successfully to {output_format} format.")
+    except Exception as e:
+        print(f"An error occurred: {e}")
+
+def main():
+    input_path = input("Enter the path to the input image: ").strip('"')
+    output_format = input("Enter the desired output format (e.g., JPEG, PNG, BMP, GIF): ").upper()
+
+    # Validate output format
+    if output_format not in ['JPEG', 'PNG', 'BMP', 'GIF']:
+        print("Invalid output format. Please choose from JPEG, PNG, BMP, or GIF.")
+        return
+
+    # Extract the file name and directory
+    file_name, file_extension = os.path.splitext(os.path.basename(input_path))
+
+    # Set the output path
+    output_path = os.path.join(os.path.dirname(input_path), f"{file_name}_converted.{output_format.lower()}")
+
+    # Convert the image
+    convert_image(input_path, output_path, output_format)
+
+if __name__ == "__main__":
+    main()

PADALA AKHIL NANDU YADAV/Task2.py

@@ -0,0 +1,35 @@
+#1. Load the DataSet:
+import seaborn as sns
+iris_df = sns.load_dataset('iris')
+
+#2. Exploratory Data Analysis (EDA):
+
+print(iris_df.info())
+print(iris_df.describe())
+print(iris_df.head())
+
+#3. Data Cleaning:
+
+print(iris_df.isnull().sum())
+print(iris_df.duplicated().sum())
+
+#4. Aggregation:
+
+species_mean = iris_df.groupby('species').mean()
+
+iris_df["species"] = iris_df["species"].map({"setosa":0,"virginica":1})
+
+#5. Visualizations:
+
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+sns.pairplot(iris_df, hue='species')
+plt.show()
+
+sns.heatmap(iris_df.corr(), annot=True, cmap='coolwarm')
+plt.show()
+
+#6. Correlation Calculations:
+
+correlation_matrix = iris_df.corr()

PADALA AKHIL NANDU YADAV/Task3.py

@@ -0,0 +1,45 @@
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+import pandas as pd
+data_url = "https://archive.ics.uci.edu/ml/machine-learning-databases/housing/housing.data"
+raw_df = pd.read_csv(data_url, sep="\s+", skiprows=22, header=None)
+data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
+target = raw_df.values[1::2, 2]
+
+# Load the Boston housing dataset
+
+X = data
+y = target
+
+# Split 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=42)
+
+# Initialize the linear regression model
+model = LinearRegression()
+
+# Fit the model on the training data
+model.fit(X_train, y_train)
+
+# Predict on the training and testing data
+y_train_pred = model.predict(X_train)
+y_test_pred = model.predict(X_test)
+
+# Calculate the scores
+train_score = model.score(X_train, y_train)
+test_score = model.score(X_test, y_test)
+
+print("Training score:", train_score)
+print("Testing score:", test_score)
+
+# Plot residuals
+plt.scatter(y_train_pred, y_train_pred - y_train, c='blue', marker='o', label='Training data')
+plt.scatter(y_test_pred, y_test_pred - y_test, c='lightgreen', marker='s', label='Testing data')
+plt.xlabel('Predicted values')
+plt.ylabel('Residuals')
+plt.legend(loc='upper left')
+plt.hlines(y=0, xmin=0, xmax=50, lw=2, color='red')
+plt.title('Residual plot')
+plt.show()

PADALA AKHIL NANDU YADAV/Task4.py

@@ -0,0 +1,59 @@
+from PIL import Image
+import os
+
+def get_size_format(b, factor=1024, suffix="B"):
+    """
+    Scale bytes to its proper byte format.
+    e.g: 1253656 => '1.20MB', 1253656678 => '1.17GB'
+    """
+    for unit in ["", "K", "M", "G", "T", "P", "E", "Z"]:
+        if b < factor:
+            return f"{b:.2f}{unit}{suffix}"
+        b /= factor
+    return f"{b:.2f}Y{suffix}"
+
+def compress_img(image_name, new_size_ratio=0.9, quality=90, width=None, height=None, to_jpg=True):
+    # Print the file path for debugging
+    print(f"[*] Attempting to open file: {image_name}")
+
+    # Load the image into memory
+    img = Image.open(image_name)
+
+    # Print the original image shape
+    print("[*] Image shape:", img.size)
+
+    # Get the original image size in bytes
+    image_size = os.path.getsize(image_name)
+    print("[*] Size before compression:", get_size_format(image_size))
+
+    if new_size_ratio < 1.0:
+        # If resizing ratio is below 1.0, multiply width & height with this ratio to reduce image size
+        img = img.resize((int(img.size[0] * new_size_ratio), int(img.size[1] * new_size_ratio)), Image.LANCZOS)
+    elif width and height:
+        # If width and height are set, resize with them instead
+        img = img.resize((width, height), Image.LANCZOS)
+
+    # Split the filename and extension
+    filename, ext = os.path.splitext(image_name)
+
+    # Convert RGBA to RGB if saving as JPEG
+    if to_jpg and img.mode == 'RGBA':
+        img = img.convert('RGB')
+
+    # Make a new filename appending "_compressed" to the original file name
+    if to_jpg:
+        # Change the extension to JPEG
+        new_filename = f"{filename}_compressed.jpg"
+    else:
+        # Retain the same extension of the original image
+        new_filename = f"{filename}_compressed{ext}"
+
+    # Save the compressed image
+    img.save(new_filename, optimize=True, quality=quality)
+
+    # Print the new image shape
+    print("[+] New Image shape:", img.size)
+    print(f"[*] Compressed image saved as: {new_filename}")
+
+# Example usage:
+compress_img(r"C:\Users\sarayu sree\Pictures\Picture1.png", new_size_ratio=0.8, quality=80, width=800, height=600)