sathvik-dl 0.1.0__tar.gz

sathvik_dl-0.1.0/PKG-INFO

@@ -0,0 +1,5 @@
+Metadata-Version: 2.4
+Name: sathvik-dl
+Version: 0.1.0
+Summary: My deep learning codes
+Requires-Python: >=3.8

sathvik_dl-0.1.0/dl.py

@@ -0,0 +1,318 @@
+codes = {}
+
+codes[5] = r'''
+import tensorflow as tf
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Embedding, GlobalAveragePooling1D, Dense
+
+# 1. Load IMDB dataset (Movie Reviews)
+(x_train, y_train), (x_test, y_test) = tf.keras.datasets.imdb.load_data(
+    num_words=10000
+)
+
+# 2. Make all reviews the same length
+x_train = tf.keras.preprocessing.sequence.pad_sequences(
+    x_train, maxlen=200
+)
+
+x_test = tf.keras.preprocessing.sequence.pad_sequences(
+    x_test, maxlen=200
+)
+
+# 3. Create deep learning model
+model = Sequential([
+    Embedding(10000, 32),
+    GlobalAveragePooling1D(),
+    Dense(64, activation='relu'),
+    Dense(1, activation='sigmoid')
+])
+
+# 4. Compile model
+model.compile(
+    optimizer='adam',
+    loss='binary_crossentropy',
+    metrics=['accuracy']
+)
+
+# 5. Train model
+model.fit(
+    x_train,
+    y_train,
+    epochs=5,
+    batch_size=32,
+    validation_split=0.2
+)
+
+# 6. Test model
+loss, accuracy = model.evaluate(x_test, y_test)
+print("Test Accuracy:", accuracy)
+
+# 7. Predict first 5 reviews
+predictions = model.predict(x_test[:5])
+
+print("\nReview Classification:")
+
+for i in range(5):
+    if predictions[i][0] >= 0.5:
+        result = "Positive"
+    else:
+        result = "Negative"
+
+    print("Review", i + 1, ":", result)
+    print("Probability:", predictions[i][0])
+
+'''
+
+codes[6] = r'''
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+from sklearn.preprocessing import MinMaxScaler
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import LSTM, Dense
+
+# 1. Generate synthetic time series data
+time = np.arange(0, 200, 0.1)
+data = np.sin(time) + 0.1 * np.random.randn(len(time))
+
+plt.plot(time, data)
+plt.title("Synthetic Time Series Data")
+plt.show()
+
+# 2. Normalize the data
+scaler = MinMaxScaler(feature_range=(0, 1))
+data_scaled = scaler.fit_transform(data.reshape(-1, 1))
+
+# 3. Create sequences
+def create_sequences(dataset, seq_length):
+    X, y = [], []
+    for i in range(len(dataset) - seq_length):
+        X.append(dataset[i:i + seq_length, 0])
+        y.append(dataset[i + seq_length, 0])
+    return np.array(X), np.array(y)
+
+SEQ_LEN = 20
+X, y = create_sequences(data_scaled, SEQ_LEN)
+
+# 4. Reshape for LSTM (samples, timesteps, features)
+X = X.reshape((X.shape[0], X.shape[1], 1))
+
+# 5. Train-test split
+split = int(len(X) * 0.8)
+X_train, X_test = X[:split], X[split:]
+y_train, y_test = y[:split], y[split:]
+
+# 6. Build LSTM model
+model = Sequential([
+    LSTM(50, activation='relu', input_shape=(SEQ_LEN, 1)),
+    Dense(1)
+])
+
+model.compile(optimizer='adam', loss='mse')
+
+# 7. Train model
+history = model.fit(
+    X_train,
+    y_train,
+    epochs=10,
+    batch_size=32,
+    validation_data=(X_test, y_test),
+    verbose=1
+)
+
+# 8. Plot training loss
+plt.plot(history.history['loss'], label='Train Loss')
+plt.plot(history.history['val_loss'], label='Validation Loss')
+plt.legend()
+plt.show()
+
+# 9. Forecast
+predictions = model.predict(X_test)
+predictions = scaler.inverse_transform(predictions.reshape(-1, 1))
+y_test_actual = scaler.inverse_transform(y_test.reshape(-1, 1))
+
+# 10. Plot predictions vs actual
+plt.plot(y_test_actual, label='Actual')
+plt.plot(predictions, label='Predicted')
+plt.legend()
+plt.show()
+'''
+
+codes[7] = r'''
+
+import tensorflow as tf
+import matplotlib.pyplot as plt
+import numpy as np
+
+# 1. Load CIFAR-10 dataset
+(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
+
+# Convert labels to 1D
+y_train = y_train.flatten()
+y_test = y_test.flatten()
+
+# 2. Resize images
+x_train = tf.image.resize(x_train, (96, 96))
+x_test = tf.image.resize(x_test, (96, 96))
+
+# 3. Load pre-trained MobileNetV2
+base_model = tf.keras.applications.MobileNetV2(
+    input_shape=(96, 96, 3),
+    include_top=False,
+    weights="imagenet"
+)
+
+# Freeze pre-trained layers
+base_model.trainable = False
+
+# 4. Create model
+model = tf.keras.Sequential([
+    base_model,
+    tf.keras.layers.GlobalAveragePooling2D(),
+    tf.keras.layers.Dense(64, activation="relu"),
+    tf.keras.layers.Dense(10, activation="softmax")
+])
+
+# 5. Compile model
+model.compile(
+    optimizer="adam",
+    loss="sparse_categorical_crossentropy",
+    metrics=["accuracy"]
+)
+
+# 6. Train model
+history = model.fit(
+    x_train,
+    y_train,
+    epochs=5,
+    batch_size=32,
+    validation_split=0.2
+)
+
+# 7. Test model
+loss, accuracy = model.evaluate(x_test, y_test)
+print("Test Accuracy:", accuracy * 100, "%")
+
+# 8. Predict one image
+prediction = model.predict(x_test[:1])
+
+classes = [
+    "airplane", "automobile", "bird", "cat", "deer",
+    "dog", "frog", "horse", "ship", "truck"
+]
+
+predicted_class = np.argmax(prediction[0])
+
+print("Actual:", classes[y_test[0]])
+print("Predicted:", classes[predicted_class])
+
+# 9. Print training and validation accuracy
+train_accuracy = history.history["accuracy"][-1]
+val_accuracy = history.history["val_accuracy"][-1]
+
+print("Training Accuracy:", train_accuracy * 100, "%")
+print("Validation Accuracy:", val_accuracy * 100, "%")
+
+# Test accuracy
+loss, test_accuracy = model.evaluate(x_test, y_test, verbose=0)
+print("Test Accuracy:", test_accuracy * 100, "%")
+
+# 10. Accuracy graph
+plt.figure(figsize=(8, 5))
+
+plt.plot(
+    history.history["accuracy"],
+    label="Training Accuracy"
+)
+
+plt.plot(
+    history.history["val_accuracy"],
+    label="Validation Accuracy"
+)
+
+plt.xlabel("Epoch")
+plt.ylabel("Accuracy")
+plt.title("Training and Validation Accuracy")
+plt.legend()
+plt.grid()
+plt.show()
+
+'''
+
+codes[8] = r'''
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import accuracy_score
+
+# Dataset
+reviews = [
+    "I loved this movie, it was fantastic",
+    "The product is excellent and very useful",
+    "Amazing experience, I really enjoyed it",
+    "The service was wonderful",
+    "Very happy with my purchase",
+    "This product is terrible",
+    "I hated this movie",
+    "Very disappointing experience",
+    "The product broke after one day",
+    "Poor quality and bad service"
+]
+
+# Labels: 1 = Positive, 0 = Negative
+labels = [
+    1, 1, 1, 1, 1,
+    0, 0, 0, 0, 0
+]
+
+# Split data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(
+    reviews,
+    labels,
+    test_size=0.2,
+    random_state=42,
+    stratify=labels
+)
+
+# Convert text into TF-IDF features
+vectorizer = TfidfVectorizer()
+
+X_train_tfidf = vectorizer.fit_transform(X_train)
+X_test_tfidf = vectorizer.transform(X_test)
+
+# Train the model
+model = LogisticRegression()
+model.fit(X_train_tfidf, y_train)
+
+# Predict test data
+y_pred = model.predict(X_test_tfidf)
+
+# Test accuracy
+print("Test Accuracy:", accuracy_score(y_test, y_pred))
+
+# Test new reviews
+new_reviews = [
+    "The movie was amazing and I loved it",
+    "The product was awful and disappointing",
+    "I am very happy with this purchase"
+]
+
+new_reviews_tfidf = vectorizer.transform(new_reviews)
+predictions = model.predict(new_reviews_tfidf)
+
+# Display results
+for review, prediction in zip(new_reviews, predictions):
+    sentiment = "Positive" if prediction == 1 else "Negative"
+    print("Review:", review)
+    print("Sentiment:", sentiment)
+
+'''
+
+def show(n):
+    print(codes[n])
+
+def run(n):
+    exec(codes[n], globals())
+
+def list_codes():
+    print("Available codes:", *codes.keys())

sathvik_dl-0.1.0/pyproject.toml

@@ -0,0 +1,12 @@
+[build-system]
+requires = ["setuptools>=61"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sathvik-dl"
+version = "0.1.0"
+description = "My deep learning codes"
+requires-python = ">=3.8"
+
+[tool.setuptools]
+py-modules = ["dl"]

sathvik_dl-0.1.0/sathvik_dl.egg-info/PKG-INFO

@@ -0,0 +1,5 @@
+Metadata-Version: 2.4
+Name: sathvik-dl
+Version: 0.1.0
+Summary: My deep learning codes
+Requires-Python: >=3.8

sathvik_dl-0.1.0/sathvik_dl.egg-info/SOURCES.txt

@@ -0,0 +1,6 @@
+dl.py
+pyproject.toml
+sathvik_dl.egg-info/PKG-INFO
+sathvik_dl.egg-info/SOURCES.txt
+sathvik_dl.egg-info/dependency_links.txt
+sathvik_dl.egg-info/top_level.txt

sathvik_dl-0.1.0/sathvik_dl.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

sathvik_dl-0.1.0/sathvik_dl.egg-info/top_level.txt

@@ -0,0 +1 @@
+dl

sathvik_dl-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+