diff --git a/.ipynb_checkpoints/stock_sentimental-checkpoint.ipynb b/.ipynb_checkpoints/stock_sentimental-checkpoint.ipynb
new file mode 100644
index 0000000..bc8b62b
--- /dev/null
+++ b/.ipynb_checkpoints/stock_sentimental-checkpoint.ipynb
@@ -0,0 +1,369 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ " Text Sentiment\n",
+ "0 Kickers on my watchlist XIDE TIT SOQ PNK CPW B... 1\n",
+ "1 user: AAP MOVIE. 55% return for the FEA/GEED i... 1\n",
+ "2 user I'd be afraid to short AMZN - they are lo... 1\n",
+ "3 MNTA Over 12.00 1\n",
+ "4 OI Over 21.37 1\n",
+ "Text 0\n",
+ "Sentiment 0\n",
+ "dtype: int64\n",
+ "(4632, 34) (4632,)\n",
+ "(1159, 34) (1159,)\n"
+ ]
+ }
+ ],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.preprocessing import LabelEncoder\n",
+ "from tensorflow.keras.preprocessing.text import Tokenizer\n",
+ "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
+ "\n",
+ "# Load dataset\n",
+ "data = pd.read_csv('Stock_data.csv')\n",
+ "\n",
+ "# Display first few rows of the dataset\n",
+ "print(data.head())\n",
+ "\n",
+ "# Check for missing values\n",
+ "print(data.isnull().sum())\n",
+ "\n",
+ "# Drop missing values if any\n",
+ "data = data.dropna()\n",
+ "\n",
+ "# Encode sentiment labels (assuming they are in a column named 'Sentiment')\n",
+ "le = LabelEncoder()\n",
+ "data['Sentiment'] = le.fit_transform(data['Sentiment'])\n",
+ "\n",
+ "# Split dataset into features and labels\n",
+ "X = data['Text']\n",
+ "y = data['Sentiment']\n",
+ "\n",
+ "# Split data into training and testing sets\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+ "\n",
+ "# Tokenization\n",
+ "tokenizer = Tokenizer(num_words=5000) # Consider top 5000 words\n",
+ "tokenizer.fit_on_texts(X_train)\n",
+ "\n",
+ "# Convert texts to sequences\n",
+ "X_train_seq = tokenizer.texts_to_sequences(X_train)\n",
+ "X_test_seq = tokenizer.texts_to_sequences(X_test)\n",
+ "\n",
+ "# Pad sequences to ensure uniform input size\n",
+ "max_length = max(len(x) for x in X_train_seq)\n",
+ "X_train_pad = pad_sequences(X_train_seq, maxlen=max_length, padding='post')\n",
+ "X_test_pad = pad_sequences(X_test_seq, maxlen=max_length, padding='post')\n",
+ "\n",
+ "# Display shapes of data\n",
+ "print(X_train_pad.shape, y_train.shape)\n",
+ "print(X_test_pad.shape, y_test.shape)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "Model: \"sequential\"\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1mModel: \"sequential\"\u001b[0m\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
+ "┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
+ "│ embedding (Embedding) │ ? │ 0 (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ lstm (LSTM) │ ? │ 0 (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dropout (Dropout) │ ? │ 0 │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ lstm_1 (LSTM) │ ? │ 0 (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dropout_1 (Dropout) │ ? │ 0 │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dense (Dense) │ ? │ 0 (unbuilt) │\n",
+ "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
+ "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
+ "│ embedding (\u001b[38;5;33mEmbedding\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ lstm (\u001b[38;5;33mLSTM\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ lstm_1 (\u001b[38;5;33mLSTM\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dense (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
+ "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Total params: 0 (0.00 B)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Trainable params: 0 (0.00 B)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Non-trainable params: 0 (0.00 B)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "from tensorflow.keras.models import Sequential\n",
+ "from tensorflow.keras.layers import Embedding, LSTM, Dense, Dropout\n",
+ "\n",
+ "# Define LSTM model\n",
+ "model = Sequential()\n",
+ "model.add(Embedding(input_dim=5000, output_dim=128)) # Embedding layer\n",
+ "model.add(LSTM(128, return_sequences=True)) # LSTM layer\n",
+ "model.add(Dropout(0.5)) # Dropout to prevent overfitting\n",
+ "model.add(LSTM(64)) # Second LSTM layer\n",
+ "model.add(Dropout(0.5)) # Dropout\n",
+ "model.add(Dense(1, activation='sigmoid')) # Output layer for binary classification\n",
+ "\n",
+ "# Compile the model\n",
+ "model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
+ "\n",
+ "# Display model summary\n",
+ "model.summary()\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Epoch 1/10\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 73ms/step - accuracy: 0.6265 - loss: 0.6656 - val_accuracy: 0.6343 - val_loss: 0.6423\n",
+ "Epoch 2/10\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 61ms/step - accuracy: 0.7415 - loss: 0.5434 - val_accuracy: 0.7573 - val_loss: 0.4971\n",
+ "Epoch 3/10\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 59ms/step - accuracy: 0.8876 - loss: 0.3093 - val_accuracy: 0.7616 - val_loss: 0.5779\n",
+ "Epoch 4/10\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 61ms/step - accuracy: 0.9329 - loss: 0.1984 - val_accuracy: 0.7519 - val_loss: 0.6860\n",
+ "Epoch 5/10\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 60ms/step - accuracy: 0.9661 - loss: 0.1211 - val_accuracy: 0.7454 - val_loss: 0.7584\n",
+ "Epoch 6/10\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 60ms/step - accuracy: 0.9642 - loss: 0.1280 - val_accuracy: 0.7357 - val_loss: 0.8707\n",
+ "Epoch 7/10\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 60ms/step - accuracy: 0.9692 - loss: 0.1043 - val_accuracy: 0.7195 - val_loss: 0.8572\n",
+ "Epoch 8/10\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 61ms/step - accuracy: 0.9730 - loss: 0.0922 - val_accuracy: 0.7335 - val_loss: 0.8631\n",
+ "Epoch 9/10\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 61ms/step - accuracy: 0.9842 - loss: 0.0609 - val_accuracy: 0.7357 - val_loss: 1.1649\n",
+ "Epoch 10/10\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 73ms/step - accuracy: 0.9794 - loss: 0.0758 - val_accuracy: 0.7228 - val_loss: 1.1020\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Train the model\n",
+ "history = model.fit(X_train_pad, y_train, epochs=10, batch_size=64, validation_split=0.2)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[1m37/37\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 14ms/step - accuracy: 0.7369 - loss: 1.0339\n",
+ "Test Accuracy: 74.46%\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Evaluate the model\n",
+ "loss, accuracy = model.evaluate(X_test_pad, y_test)\n",
+ "print(f'Test Accuracy: {accuracy * 100:.2f}%')\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 500ms/step\n",
+ "Sentiment: Positive\n"
+ ]
+ }
+ ],
+ "source": [
+ "def predict_sentiment(text):\n",
+ " sequence = tokenizer.texts_to_sequences([text])\n",
+ " padded = pad_sequences(sequence, maxlen=max_length, padding='post')\n",
+ " prediction = model.predict(padded)\n",
+ " # Assuming binary classification: 0 for Negative, 1 for Positive\n",
+ " if prediction[0] > 0.5:\n",
+ " print(\"Sentiment: Positive\")\n",
+ " else:\n",
+ " print(\"Sentiment: Negative\")\n",
+ "\n",
+ "# Example usage\n",
+ "new_text = \"The stock market is bad today.\"\n",
+ "predict_sentiment(new_text)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model.save('sentiment_model.keras')\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Text: \"The stock market is performing well today.\"\n",
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step\n",
+ "Sentiment: Positive\n",
+ "Text: \"The stock market is performing bad today.\"\n",
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n",
+ "Sentiment: Positive\n",
+ "Text: \"I'm very happy with the profits I've made.\"\n",
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step\n",
+ "Sentiment: Positive\n",
+ "Text: \"I'm disappointed with the losses this quarter.\"\n",
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step\n",
+ "Sentiment: Negative\n",
+ "Text: \"It's a great time to invest in stocks!\"\n",
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step\n",
+ "Sentiment: Positive\n"
+ ]
+ }
+ ],
+ "source": [
+ "test_texts = [\n",
+ " \"The stock market is performing well today.\",\n",
+ " \"The stock market is performing bad today.\",\n",
+ " \"I'm very happy with the profits I've made.\",\n",
+ " \"I'm disappointed with the losses this quarter.\",\n",
+ " \"It's a great time to invest in stocks!\"\n",
+ " \n",
+ "]\n",
+ "\n",
+ "for text in test_texts:\n",
+ " print(f'Text: \"{text}\"')\n",
+ " predict_sentiment(text)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.12.4"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/PROJECT_STRUCTURE.md b/PROJECT_STRUCTURE.md
index 1ed8936..088af5f 100644
--- a/PROJECT_STRUCTURE.md
+++ b/PROJECT_STRUCTURE.md
@@ -15,6 +15,10 @@
│ ├── SBI Test data.csv
│ ├── SBI Train data.csv
│ └── SBIN.csv
+├── Data Analysis/
+│ ├── SBI Stock Analysis .png
+│ ├── SBI Stock Analysis Updated.pptx
+│ └── SBI Stock Analysis Updated.twbx
├── Financial Environment Segmentation/
│ ├── Financial Environment Segmentation.ipynb
│ ├── Financial Insights - Market Segmentation.png
diff --git a/repo_structure.txt b/repo_structure.txt
index 3af122d..149e9b4 100644
--- a/repo_structure.txt
+++ b/repo_structure.txt
@@ -11,6 +11,10 @@
│ ├── SBI Test data.csv
│ ├── SBI Train data.csv
│ └── SBIN.csv
+├── Data Analysis/
+│ ├── SBI Stock Analysis .png
+│ ├── SBI Stock Analysis Updated.pptx
+│ └── SBI Stock Analysis Updated.twbx
├── Financial Environment Segmentation/
│ ├── Financial Environment Segmentation.ipynb
│ ├── Financial Insights - Market Segmentation.png
diff --git a/sentiment_model.h5 b/sentiment_model.h5
index 3183c43..8b6b6a8 100644
Binary files a/sentiment_model.h5 and b/sentiment_model.h5 differ
diff --git a/sentiment_model.keras b/sentiment_model.keras
new file mode 100644
index 0000000..457085e
Binary files /dev/null and b/sentiment_model.keras differ
diff --git a/stock_sentimental.ipynb b/stock_sentimental.ipynb
index 746daff..bc8b62b 100644
--- a/stock_sentimental.ipynb
+++ b/stock_sentimental.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 2,
"metadata": {},
"outputs": [
{
@@ -74,25 +74,17 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 3,
"metadata": {},
"outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "c:\\Users\\sapni\\anaconda3\\lib\\site-packages\\keras\\src\\layers\\core\\embedding.py:90: UserWarning: Argument `input_length` is deprecated. Just remove it.\n",
- " warnings.warn(\n"
- ]
- },
{
"data": {
"text/html": [
- "Model: \"sequential_1\"\n",
+ "Model: \"sequential\"\n",
"\n"
],
"text/plain": [
- "\u001b[1mModel: \"sequential_1\"\u001b[0m\n"
+ "\u001b[1mModel: \"sequential\"\u001b[0m\n"
]
},
"metadata": {},
@@ -101,39 +93,39 @@
{
"data": {
"text/html": [
- "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
- "┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
- "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
- "│ embedding_1 (Embedding) │ ? │ 0 (unbuilt) │\n",
- "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
- "│ lstm_2 (LSTM) │ ? │ 0 (unbuilt) │\n",
- "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
- "│ dropout_2 (Dropout) │ ? │ 0 │\n",
- "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
- "│ lstm_3 (LSTM) │ ? │ 0 (unbuilt) │\n",
- "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
- "│ dropout_3 (Dropout) │ ? │ 0 │\n",
- "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
- "│ dense_1 (Dense) │ ? │ 0 (unbuilt) │\n",
- "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
+ "┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
+ "│ embedding (Embedding) │ ? │ 0 (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ lstm (LSTM) │ ? │ 0 (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dropout (Dropout) │ ? │ 0 │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ lstm_1 (LSTM) │ ? │ 0 (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dropout_1 (Dropout) │ ? │ 0 │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dense (Dense) │ ? │ 0 (unbuilt) │\n",
+ "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
"\n"
],
"text/plain": [
- "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
- "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
- "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
- "│ embedding_1 (\u001b[38;5;33mEmbedding\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
- "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
- "│ lstm_2 (\u001b[38;5;33mLSTM\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
- "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
- "│ dropout_2 (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n",
- "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
- "│ lstm_3 (\u001b[38;5;33mLSTM\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
- "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
- "│ dropout_3 (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n",
- "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
- "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
- "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
+ "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
+ "│ embedding (\u001b[38;5;33mEmbedding\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ lstm (\u001b[38;5;33mLSTM\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ lstm_1 (\u001b[38;5;33mLSTM\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+ "│ dense (\u001b[38;5;33mDense\u001b[0m) │ ? │ \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
+ "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n"
]
},
"metadata": {},
@@ -185,7 +177,7 @@
"\n",
"# Define LSTM model\n",
"model = Sequential()\n",
- "model.add(Embedding(input_dim=5000, output_dim=128, input_length=max_length)) # Embedding layer\n",
+ "model.add(Embedding(input_dim=5000, output_dim=128)) # Embedding layer\n",
"model.add(LSTM(128, return_sequences=True)) # LSTM layer\n",
"model.add(Dropout(0.5)) # Dropout to prevent overfitting\n",
"model.add(LSTM(64)) # Second LSTM layer\n",
@@ -201,7 +193,7 @@
},
{
"cell_type": "code",
- "execution_count": 14,
+ "execution_count": 6,
"metadata": {},
"outputs": [
{
@@ -209,25 +201,25 @@
"output_type": "stream",
"text": [
"Epoch 1/10\n",
- "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 67ms/step - accuracy: 0.6284 - loss: 0.6606 - val_accuracy: 0.6268 - val_loss: 0.6536\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 73ms/step - accuracy: 0.6265 - loss: 0.6656 - val_accuracy: 0.6343 - val_loss: 0.6423\n",
"Epoch 2/10\n",
- "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 61ms/step - accuracy: 0.7146 - loss: 0.5622 - val_accuracy: 0.7745 - val_loss: 0.4920\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 61ms/step - accuracy: 0.7415 - loss: 0.5434 - val_accuracy: 0.7573 - val_loss: 0.4971\n",
"Epoch 3/10\n",
- "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 75ms/step - accuracy: 0.8898 - loss: 0.3168 - val_accuracy: 0.7756 - val_loss: 0.4849\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 59ms/step - accuracy: 0.8876 - loss: 0.3093 - val_accuracy: 0.7616 - val_loss: 0.5779\n",
"Epoch 4/10\n",
- "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 71ms/step - accuracy: 0.9278 - loss: 0.2154 - val_accuracy: 0.7433 - val_loss: 0.5643\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 61ms/step - accuracy: 0.9329 - loss: 0.1984 - val_accuracy: 0.7519 - val_loss: 0.6860\n",
"Epoch 5/10\n",
- "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 71ms/step - accuracy: 0.9486 - loss: 0.1725 - val_accuracy: 0.7594 - val_loss: 0.6393\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 60ms/step - accuracy: 0.9661 - loss: 0.1211 - val_accuracy: 0.7454 - val_loss: 0.7584\n",
"Epoch 6/10\n",
- "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 62ms/step - accuracy: 0.9671 - loss: 0.1213 - val_accuracy: 0.7530 - val_loss: 0.8493\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 60ms/step - accuracy: 0.9642 - loss: 0.1280 - val_accuracy: 0.7357 - val_loss: 0.8707\n",
"Epoch 7/10\n",
- "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 62ms/step - accuracy: 0.9738 - loss: 0.0973 - val_accuracy: 0.7357 - val_loss: 1.0902\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 60ms/step - accuracy: 0.9692 - loss: 0.1043 - val_accuracy: 0.7195 - val_loss: 0.8572\n",
"Epoch 8/10\n",
- "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 64ms/step - accuracy: 0.9737 - loss: 0.0950 - val_accuracy: 0.7357 - val_loss: 0.8958\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 61ms/step - accuracy: 0.9730 - loss: 0.0922 - val_accuracy: 0.7335 - val_loss: 0.8631\n",
"Epoch 9/10\n",
- "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 68ms/step - accuracy: 0.9826 - loss: 0.0744 - val_accuracy: 0.7443 - val_loss: 0.9316\n",
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 61ms/step - accuracy: 0.9842 - loss: 0.0609 - val_accuracy: 0.7357 - val_loss: 1.1649\n",
"Epoch 10/10\n",
- "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 75ms/step - accuracy: 0.9851 - loss: 0.0689 - val_accuracy: 0.7303 - val_loss: 1.0088\n"
+ "\u001b[1m58/58\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 73ms/step - accuracy: 0.9794 - loss: 0.0758 - val_accuracy: 0.7228 - val_loss: 1.1020\n"
]
}
],
@@ -238,15 +230,15 @@
},
{
"cell_type": "code",
- "execution_count": 15,
+ "execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "\u001b[1m37/37\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - accuracy: 0.7407 - loss: 0.9643\n",
- "Test Accuracy: 74.63%\n"
+ "\u001b[1m37/37\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 14ms/step - accuracy: 0.7369 - loss: 1.0339\n",
+ "Test Accuracy: 74.46%\n"
]
}
],
@@ -258,19 +250,15 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 10,
"metadata": {},
"outputs": [
{
- "ename": "NameError",
- "evalue": "name 'tokenizer' is not defined",
- "output_type": "error",
- "traceback": [
- "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)",
- "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_10044\\3289756518.py\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 11\u001b[0m \u001b[1;31m# Example usage\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 12\u001b[0m \u001b[0mnew_text\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m\"The stock market is bad today.\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 13\u001b[1;33m \u001b[0mpredict_sentiment\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnew_text\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
- "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_10044\\3289756518.py\u001b[0m in \u001b[0;36mpredict_sentiment\u001b[1;34m(text)\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mpredict_sentiment\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtext\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0msequence\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtokenizer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtexts_to_sequences\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mtext\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3\u001b[0m \u001b[0mpadded\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpad_sequences\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msequence\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmaxlen\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmax_length\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpadding\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'post'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0mprediction\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpadded\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[1;31m# Assuming binary classification: 0 for Negative, 1 for Positive\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
- "\u001b[1;31mNameError\u001b[0m: name 'tokenizer' is not defined"
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 500ms/step\n",
+ "Sentiment: Positive\n"
]
}
],
@@ -292,25 +280,17 @@
},
{
"cell_type": "code",
- "execution_count": 17,
+ "execution_count": 14,
"metadata": {},
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
- ]
- }
- ],
+ "outputs": [],
"source": [
- "model.save('sentiment_model.h5')\n",
+ "model.save('sentiment_model.keras')\n",
"\n"
]
},
{
"cell_type": "code",
- "execution_count": 18,
+ "execution_count": 16,
"metadata": {},
"outputs": [
{
@@ -318,19 +298,19 @@
"output_type": "stream",
"text": [
"Text: \"The stock market is performing well today.\"\n",
- "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step\n",
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step\n",
"Sentiment: Positive\n",
"Text: \"The stock market is performing bad today.\"\n",
- "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step\n",
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n",
"Sentiment: Positive\n",
"Text: \"I'm very happy with the profits I've made.\"\n",
- "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 59ms/step\n",
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step\n",
"Sentiment: Positive\n",
"Text: \"I'm disappointed with the losses this quarter.\"\n",
- "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step\n",
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 53ms/step\n",
"Sentiment: Negative\n",
"Text: \"It's a great time to invest in stocks!\"\n",
- "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step\n",
+ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step\n",
"Sentiment: Positive\n"
]
}
@@ -367,7 +347,7 @@
],
"metadata": {
"kernelspec": {
- "display_name": "base",
+ "display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@@ -381,9 +361,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.9.13"
+ "version": "3.12.4"
}
},
"nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
}