package-loader 1.0.0__tar.gz

package_loader-1.0.0/PKG-INFO

@@ -0,0 +1,24 @@
+Metadata-Version: 2.4
+Name: package-loader
+Version: 1.0.0
+Summary: CLI tool to download DL, NLP, and HPC codes
+Author: Jhony
+Requires-Python: >=3.7
+Requires-Dist: requests
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: matplotlib
+Requires-Dist: scikit-learn
+Requires-Dist: nltk
+Provides-Extra: dl
+Requires-Dist: torch; extra == "dl"
+Requires-Dist: tensorflow; extra == "dl"
+Provides-Extra: all
+Requires-Dist: torch; extra == "all"
+Requires-Dist: tensorflow; extra == "all"
+Requires-Dist: gensim; extra == "all"
+Dynamic: author
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary

package_loader-1.0.0/mycodes/__init__.py

@@ -0,0 +1,9 @@
+"""
+MyCode CLI - Download DL, NLP, and HPC practicals
+"""
+
+from .cli import main
+from .downloader import get_item
+
+__all__ = ["main", "get_item"]
+__version__ = "1.0"

package_loader-1.0.0/mycodes/cli.py

@@ -0,0 +1,139 @@
+# cli.py
+"""
+Command-line interface for dataset downloads.
+
+Usage:
+    mycodes get <dataset_name>        Download a specific dataset
+    mycodes list                      List all available datasets
+    mycodes list <category>           List datasets in a category (dl, nlp, hpc)
+    mycodes help                      Show help message
+"""
+
+import sys
+from .downloader import (
+    get_item,
+    list_all_datasets,
+    get_category_datasets,
+    DownloadError,
+    DatasetNotFoundError,
+    DownloadFailedError,
+)
+from .registry import initialize_registry
+
+
+def show_help():
+    """Display help information."""
+    help_text = """
+MyCode CLI - Download DL, NLP, and HPC datasets
+
+USAGE:
+    mycodes get <name>          Download a dataset
+    mycodes list                List all datasets
+    mycodes list <category>     List datasets in a category
+    mycodes help                Show this help message
+
+EXAMPLES:
+    mycodes get boston          Download Boston housing dataset
+    mycodes get nlp2            Download NLP2 car dataset
+    mycodes get 1bfs            Download BFS/DFS HPC code
+    
+    mycodes list                Show all available datasets
+    mycodes list dl             Show all deep learning datasets
+    mycodes list nlp            Show all NLP datasets
+    mycodes list hpc            Show all HPC datasets
+
+CATEGORIES:
+    dl                          Deep Learning datasets
+    nlp                         Natural Language Processing datasets
+    hpc                         High Performance Computing code files
+    """
+    print(help_text)
+
+
+def show_list(category: str = None):
+    """Display available datasets."""
+    datasets = list_all_datasets()
+
+    if category:
+        if category not in datasets:
+            print(f"Error: Unknown category '{category}'")
+            print(f"Available categories: {', '.join(sorted(datasets.keys()))}")
+            return False
+
+        items = datasets[category]
+        print(f"\n{category.upper()} Datasets:")
+        print("-" * 60)
+        for name, desc in sorted(items.items()):
+            print(f"  {name:<20} - {desc}")
+        return True
+
+    # Show all categories
+    for cat in sorted(datasets.keys()):
+        items = datasets[cat]
+        print(f"\n{cat.upper()} Datasets:")
+        print("-" * 60)
+        for name, desc in sorted(items.items()):
+            print(f"  {name:<20} - {desc}")
+
+    return True
+
+
+def main():
+    """Main CLI entry point."""
+    # Initialize registry on first run
+    initialize_registry()
+
+    if len(sys.argv) < 2:
+        print("Usage: mycodes <command> [args]")
+        print("Try 'mycodes help' for more information")
+        sys.exit(1)
+
+    command = sys.argv[1].lower()
+
+    try:
+        if command == "get":
+            if len(sys.argv) < 3:
+                print("Error: 'get' command requires a dataset name")
+                print("Usage: mycodes get <dataset_name>")
+                print("Try 'mycodes list' to see available datasets")
+                sys.exit(1)
+
+            dataset_name = sys.argv[2]
+            print(f"Downloading '{dataset_name}'...")
+
+            try:
+                result = get_item(dataset_name)
+                print(f"✓ Success: Downloaded to {result}")
+                sys.exit(0)
+            except DatasetNotFoundError as e:
+                print(f"✗ Error: {e}")
+                sys.exit(1)
+            except DownloadFailedError as e:
+                print(f"✗ Download failed: {e}")
+                sys.exit(1)
+
+        elif command == "list":
+            category = sys.argv[2].lower() if len(sys.argv) > 2 else None
+            success = show_list(category)
+            sys.exit(0 if success else 1)
+
+        elif command == "help":
+            show_help()
+            sys.exit(0)
+
+        else:
+            print(f"Error: Unknown command '{command}'")
+            print("Available commands: get, list, help")
+            print("Try 'mycodes help' for more information")
+            sys.exit(1)
+
+    except DownloadError as e:
+        print(f"Download Error: {e}", file=sys.stderr)
+        sys.exit(1)
+    except Exception as e:
+        print(f"Unexpected error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

package_loader-1.0.0/mycodes/dl/__init__.py

@@ -0,0 +1,7 @@
+"""Deep Learning practicals
+
+This module provides lazy-loaded access to deep learning datasets.
+Do NOT import models to avoid executing model logic at import time.
+"""
+
+__all__ = []

package_loader-1.0.0/mycodes/dl/boston/__init__.py

@@ -0,0 +1 @@
+from .dataset import download_data

package_loader-1.0.0/mycodes/dl/boston/dataset.py

@@ -0,0 +1,40 @@
+"""
+Boston Housing Price Prediction Dataset downloader.
+
+This module provides lazy-loaded dataset downloads without executing model logic.
+No imports of heavy libraries happen at module level.
+"""
+
+import os
+import requests
+
+
+URL = "https://raw.githubusercontent.com/Vishwajeet-Londhe/SPPU-CSE-SEM8-Codes/refs/heads/master/LP-V/DL/1.Boston%20housing%20price/1_boston_housing.csv"
+PATH = os.path.join(os.getcwd(), "data", "boston.csv")
+
+
+def download_data():
+    """
+    Download Boston Housing Price dataset.
+
+    Returns:
+        str: Path to the downloaded dataset file
+
+    Raises:
+        RuntimeError: If download fails
+    """
+    if os.path.exists(PATH):
+        print("Already exists")
+        return PATH
+
+    os.makedirs(os.path.dirname(PATH), exist_ok=True)
+
+    try:
+        r = requests.get(URL)
+        r.raise_for_status()
+        with open(PATH, "wb") as f:
+            f.write(r.content)
+        print(f"Downloaded to {PATH}")
+        return PATH
+    except requests.RequestException as e:
+        raise RuntimeError(f"Failed to download dataset: {e}")

package_loader-1.0.0/mycodes/dl/boston/model.py

@@ -0,0 +1,89 @@
+#Step 1: Import Libraries
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+
+import tensorflow as tf
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense
+#Step 2: Load Dataset
+# Load dataset
+df = pd.read_csv("1_boston_housing.csv")
+
+# Remove quotes from column names (important for your dataset)
+df.columns = df.columns.str.replace('"', '')
+
+# Display first 5 rows
+df.head()
+#Step 3: Split Features and Target
+X = df.drop("MEDV", axis=1)   # Features
+y = df["MEDV"]                # Target
+
+print(X.shape, y.shape)
+#Step 4: Train-Test Split
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size=0.2, random_state=42
+)
+#Step 5: Feature Scaling
+scaler = StandardScaler()
+
+X_train = scaler.fit_transform(X_train)
+X_test = scaler.transform(X_test)
+model = Sequential()
+model.add(Dense(1, input_shape=(X_train.shape[1],), activation='linear'))
+
+model.compile(
+    optimizer='adam',
+    loss='mse',
+    metrics=['mae']
+)
+
+history = model.fit(
+    X_train, y_train,
+    epochs=100,
+    validation_split=0.05,
+    verbose=1
+)
+#Step 6: Build Deep Neural Network
+model = Sequential()
+
+# Single neuron → behaves like linear regression
+model.add(Dense(1, input_shape=(X_train.shape[1],), activation='linear'))
+
+model.compile(
+    optimizer='adam',
+    loss='mse',
+    metrics=['mae']
+)
+
+model.summary()
+#Step 7: Train Model
+history = model.fit(
+    X_train, y_train,
+    epochs=100,
+    batch_size=16,
+    validation_split=0.2,
+    verbose=1
+)
+#Step 8: Evaluate Model
+loss, mae = model.evaluate(X_test, y_test)
+
+print("Test Loss (MSE):", loss)
+print("Test MAE:", mae)
+#Step 9: Predictions
+y_pred = model.predict(X_test)
+
+# Compare actual vs predicted
+for i in range(5):
+    print(f"Actual: {y_test.iloc[i]:.2f} | Predicted: {y_pred[i][0]:.2f}")
+#Step 10: Plot Training Graphs
+plt.plot(history.history['loss'], label='Training Loss')
+plt.plot(history.history['val_loss'], label='Validation Loss')
+plt.legend()
+plt.title("Loss Graph")
+plt.xlabel("Epochs")
+plt.ylabel("Loss")
+plt.show()

package_loader-1.0.0/mycodes/dl/imdb/__init__.py

@@ -0,0 +1 @@
+from .dataset import download_data

package_loader-1.0.0/mycodes/dl/imdb/dataset.py

@@ -0,0 +1,40 @@
+"""
+IMDB Movie Reviews Dataset downloader.
+
+This module provides lazy-loaded dataset downloads without executing model logic.
+No imports of heavy libraries happen at module level.
+"""
+
+import os
+import requests
+
+
+URL = "https://github.com/Vishwajeet-Londhe/SPPU-CSE-SEM8-Codes/raw/refs/heads/master/LP-V/DL/2.IMDB/IMDB_Dataset.csv"
+PATH = os.path.join(os.getcwd(), "data", "imdb.csv")
+
+
+def download_data():
+    """
+    Download IMDB Movie Reviews dataset.
+
+    Returns:
+        str: Path to the downloaded dataset file
+
+    Raises:
+        RuntimeError: If download fails
+    """
+    if os.path.exists(PATH):
+        print("Already exists")
+        return PATH
+
+    os.makedirs(os.path.dirname(PATH), exist_ok=True)
+
+    try:
+        r = requests.get(URL)
+        r.raise_for_status()
+        with open(PATH, "wb") as f:
+            f.write(r.content)
+        print(f"Downloaded to {PATH}")
+        return PATH
+    except requests.RequestException as e:
+        raise RuntimeError(f"Failed to download dataset: {e}")

package_loader-1.0.0/mycodes/dl/imdb/model.py

@@ -0,0 +1,112 @@
+# =========================
+# 1. IMPORT LIBRARIES
+# =========================
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import re
+
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense
+# =========================
+# 2. LOAD DATASET (SAFE)
+# =========================
+df = pd.read_csv(
+    "IMDB_Dataset.csv",
+    encoding_errors='ignore',
+    on_bad_lines='skip',
+    engine='python'
+)
+
+print("Dataset Loaded ✅")
+print(df.head())
+print(df.columns)
+df = df.dropna()
+print(df['sentiment'].unique())
+print(df['sentiment'].isnull().sum())
+df = df.dropna()
+
+print(df['sentiment'].unique())   # should be [0,1]
+print(df.isnull().sum())          # should be 0
+# =========================
+# 3. FIX COLUMN NAMES
+# =========================
+df.columns = ['review', 'sentiment']
+# =========================
+# 4. CLEAN TEXT
+# =========================
+def clean_text(text):
+    text = str(text)
+    text = text.lower()
+    text = re.sub(r'<.*?>', '', text)      # remove HTML
+    text = re.sub(r'[^a-zA-Z ]', '', text) # remove symbols
+    return text
+
+df['review'] = df['review'].apply(clean_text)
+# =========================
+# 5. CONVERT LABELS
+# =========================
+df['sentiment'] = df['sentiment'].map({'positive': 1, 'negative': 0})
+
+print("\nSentiment Count:")
+print(df['sentiment'].value_counts())
+# =========================
+# 6. TF-IDF VECTORIZATION
+# =========================
+vectorizer = TfidfVectorizer(max_features=5000)
+X = vectorizer.fit_transform(df['review']).toarray()
+y = df['sentiment']
+
+# =========================
+# 7. TRAIN TEST SPLIT
+# =========================
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size=0.2, random_state=42
+)
+
+# =========================
+# 8. BUILD MODEL
+# =========================
+model = Sequential()
+
+model.add(Dense(128, activation='relu', input_shape=(X_train.shape[1],)))
+model.add(Dense(64, activation='relu'))
+model.add(Dense(1, activation='sigmoid'))
+
+model.compile(
+    optimizer='adam',
+    loss='binary_crossentropy',
+    metrics=['accuracy']
+)
+
+model.summary()
+
+
+# =========================
+# 9. TRAIN MODEL
+# =========================
+history = model.fit(
+    X_train, y_train,
+    epochs=10,
+    batch_size=32,
+    validation_data=(X_test, y_test)
+)
+# =========================
+# 10. PLOT GRAPH
+# =========================
+plt.plot(history.history['accuracy'], label='Training Accuracy')
+plt.plot(history.history['val_accuracy'], label='Validation Accuracy')
+
+plt.title("Accuracy Graph")
+plt.xlabel("Epochs")
+plt.ylabel("Accuracy")
+plt.legend()
+plt.show()
+# =========================
+# 11. FINAL ACCURACY
+# =========================
+loss, accuracy = model.evaluate(X_test, y_test)
+print("\nFinal Accuracy:", accuracy)

package_loader-1.0.0/mycodes/dl/plant_disease/dataset.py

@@ -0,0 +1,37 @@
+"""
+Plant Disease Classification Dataset downloader.
+
+This module provides lazy-loaded dataset downloads without executing model logic.
+No imports of heavy libraries happen at module level.
+"""
+
+import os
+import requests
+
+
+URL = "https://github.com/Vishwajeet-Londhe/SPPU-CSE-SEM8-Codes/raw/refs/heads/master/LP-V/DL/3.Plant_Disease/plant_disease_data.csv"
+PATH = os.path.join(os.getcwd(), "data", "plant_disease.csv")
+
+
+def download_data():
+    """
+    Download plant disease classification dataset.
+
+    Returns:
+        str: Path to the downloaded dataset file
+    """
+    if os.path.exists(PATH):
+        print("Already exists")
+        return PATH
+
+    os.makedirs(os.path.dirname(PATH), exist_ok=True)
+
+    try:
+        r = requests.get(URL)
+        r.raise_for_status()
+        with open(PATH, "wb") as f:
+            f.write(r.content)
+        print(f"Downloaded to {PATH}")
+        return PATH
+    except requests.RequestException as e:
+        raise RuntimeError(f"Failed to download dataset: {e}")

package_loader-1.0.0/mycodes/dl/plant_disease/model.py

@@ -0,0 +1,81 @@
+import tensorflow as tf
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+import matplotlib.pyplot as plt
+train_path = "Plant_Disease_Dataset/train"
+valid_path = "Plant_Disease_Dataset/valid"
+test_path  = "Plant_Disease_Dataset/test"
+train_datagen = ImageDataGenerator(
+    rescale=1./255,
+    rotation_range=20,
+    zoom_range=0.2,
+    horizontal_flip=True
+)
+
+valid_datagen = ImageDataGenerator(rescale=1./255)
+test_datagen  = ImageDataGenerator(rescale=1./255)
+train_data = train_datagen.flow_from_directory(
+    train_path,
+    target_size=(128, 128),
+    batch_size=32,
+    class_mode='categorical'
+)
+
+valid_data = valid_datagen.flow_from_directory(
+    valid_path,
+    target_size=(128, 128),
+    batch_size=32,
+    class_mode='categorical'
+)
+
+test_data = test_datagen.flow_from_directory(
+    test_path,
+    target_size=(128, 128),
+    batch_size=32,
+    class_mode='categorical'
+)
+model = Sequential()
+
+# Conv Layer 1
+model.add(Conv2D(32, (3,3), activation='relu', input_shape=(128,128,3)))
+model.add(MaxPooling2D(2,2))
+
+# Conv Layer 2
+model.add(Conv2D(64, (3,3), activation='relu'))
+model.add(MaxPooling2D(2,2))
+
+# Conv Layer 3
+model.add(Conv2D(128, (3,3), activation='relu'))
+model.add(MaxPooling2D(2,2))
+
+# Flatten
+model.add(Flatten())
+
+# Fully Connected
+model.add(Dense(128, activation='relu'))
+model.add(Dropout(0.5))
+
+# Output Layer
+model.add(Dense(train_data.num_classes, activation='softmax'))
+
+model.compile(
+    optimizer='adam',
+    loss='categorical_crossentropy',
+    metrics=['accuracy']
+)
+
+model.summary()
+history = model.fit(
+    train_data,
+    epochs=3,
+    validation_data=valid_data
+)
+plt.plot(history.history['accuracy'], label='Training Accuracy')
+plt.plot(history.history['val_accuracy'], label='Validation Accuracy')
+
+plt.title("CNN Accuracy Graph")
+plt.xlabel("Epochs")
+plt.ylabel("Accuracy")
+plt.legend()
+plt.show()

package_loader-1.0.0/mycodes/dl/stock/__init__.py

@@ -0,0 +1 @@
+from .dataset import download_data

package_loader-1.0.0/mycodes/dl/stock/dataset.py

@@ -0,0 +1,40 @@
+"""
+Google Stock Price Dataset downloader.
+
+This module provides lazy-loaded dataset downloads without executing model logic.
+No imports of heavy libraries happen at module level.
+"""
+
+import os
+import requests
+
+
+URL = "https://raw.githubusercontent.com/Vishwajeet-Londhe/SPPU-CSE-SEM8-Codes/refs/heads/master/LP-V/DL/4.Google_Stock_Price/Google_Stock_Price.csv"
+PATH = os.path.join(os.getcwd(), "data", "stock.csv")
+
+
+def download_data():
+    """
+    Download Google Stock Price dataset.
+
+    Returns:
+        str: Path to the downloaded dataset file
+
+    Raises:
+        RuntimeError: If download fails
+    """
+    if os.path.exists(PATH):
+        print("Already exists")
+        return PATH
+
+    os.makedirs(os.path.dirname(PATH), exist_ok=True)
+
+    try:
+        r = requests.get(URL)
+        r.raise_for_status()
+        with open(PATH, "wb") as f:
+            f.write(r.content)
+        print(f"Downloaded to {PATH}")
+        return PATH
+    except requests.RequestException as e:
+        raise RuntimeError(f"Failed to download dataset: {e}")

package_loader-1.0.0/mycodes/dl/stock/model.py

@@ -0,0 +1,56 @@
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+from sklearn.preprocessing import MinMaxScaler
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense, SimpleRNN
+#2. Load Dataset
+df = pd.read_csv("Google_Stock_Price.csv", thousands=',')
+
+# Take Open column
+data = df['Open'].values.reshape(-1, 1)
+scaler = MinMaxScaler(feature_range=(0,1))
+# Clean non-numeric values like 'GOOGL' / NaN from Open column, then scale
+data = pd.to_numeric(df['Open'], errors='coerce').dropna().values.reshape(-1, 1)
+data_scaled = scaler.fit_transform(data)
+train_size = int(len(data_scaled) * 0.8)
+
+train_data = data_scaled[:train_size]
+test_data = data_scaled[train_size:]
+def create_dataset(dataset):
+    X = []
+    y = []
+    
+    for i in range(60, len(dataset)):
+        X.append(dataset[i-60:i, 0])
+        y.append(dataset[i, 0])
+    
+    return np.array(X), np.array(y)
+
+X_train, y_train = create_dataset(train_data)
+X_test, y_test = create_dataset(test_data)
+X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))
+X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))
+model = Sequential()
+
+model.add(SimpleRNN(50, return_sequences=True, input_shape=(60,1)))
+model.add(SimpleRNN(50))
+model.add(Dense(1))
+
+model.compile(optimizer='adam', loss='mean_squared_error')
+
+model.summary()
+model.fit(X_train, y_train, epochs=20, batch_size=32)
+predicted = model.predict(X_test)
+
+predicted = scaler.inverse_transform(predicted)
+real = scaler.inverse_transform(y_test.reshape(-1,1))
+plt.plot(real, color='red', label='Real Price')
+plt.plot(predicted, color='blue', label='Predicted Price')
+
+plt.title("Google Stock Price Prediction (RNN)")
+plt.xlabel("Time")
+plt.ylabel("Price")
+plt.legend()
+plt.show()