Merge pull request #849 from abckhush/main

Tesla Historic Stock Price Analysis

Tesla Historic Stock Price Analysis/Dataset/README.md

@@ -0,0 +1,13 @@
+# **Tesla Ticker | Historical Stock Price Dataset**
+
+This dataset contains the historical stock prices of Tesla, Inc. (TSLA).
+
+### Insights
+- Analyze historical trends in Tesla's stock price
+- Forecast future stock price movements
+
+### Source
+Acquired from the Yahoo Finance library
+
+### Dataset Link 
+https://www.kaggle.com/datasets/muhammadibrahimqasmi/tesla-stock-insights-and-predictions/data

Tesla Historic Stock Price Analysis/Model/tesla-ticker-bigru.ipynb

@@ -0,0 +1 @@
+{"cells":[{"cell_type":"markdown","metadata":{},"source":["# Tesla Ticker| Histroical Stock Price Dataset| GRU| BiGRU"]},{"cell_type":"code","execution_count":1,"metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","execution":{"iopub.execute_input":"2024-06-20T17:33:21.834984Z","iopub.status.busy":"2024-06-20T17:33:21.834489Z","iopub.status.idle":"2024-06-20T17:33:42.911579Z","shell.execute_reply":"2024-06-20T17:33:42.910348Z","shell.execute_reply.started":"2024-06-20T17:33:21.834946Z"},"trusted":true},"outputs":[{"name":"stderr","output_type":"stream","text":["2024-06-20 17:33:29.010197: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n","2024-06-20 17:33:29.010414: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n","2024-06-20 17:33:29.195465: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n"]}],"source":["# Import Libararies\n","import pandas as pd\n","import seaborn as sns\n","import matplotlib.pyplot as plt\n","import numpy as np\n","# implort plotly for interactive plots\n","import plotly.express as px\n","import plotly.graph_objects as go\n","from plotly.offline import iplot\n","#import plot_acf\n","from statsmodels.graphics.tsaplots import plot_acf\n","# import seasonal decompose\n","from statsmodels.tsa.seasonal import seasonal_decompose\n","# scaler\n","from sklearn.preprocessing import MinMaxScaler\n","# train_test_split\n","from sklearn.model_selection import train_test_split\n","# sequential using keras\n","from tensorflow.keras.models import Sequential\n","# Dense, Bidirectional,GRU Layers using keras\n","from tensorflow.keras.layers import Dense, Bidirectional, GRU\n","# Adam optimizer\n","from tensorflow.keras.optimizers import Adam\n","# Early stoppng or callbacks\n","from tensorflow.keras.callbacks import EarlyStopping\n","# import metrics\n","from sklearn.metrics import r2_score, mean_squared_error\n","# import warnings\n","import warnings \n","warnings.filterwarnings('ignore')"]},{"cell_type":"markdown","metadata":{},"source":["## BiGRU"]},{"cell_type":"code","execution_count":27,"metadata":{"execution":{"iopub.execute_input":"2024-06-20T17:38:25.753838Z","iopub.status.busy":"2024-06-20T17:38:25.753284Z","iopub.status.idle":"2024-06-20T17:39:00.332807Z","shell.execute_reply":"2024-06-20T17:39:00.331452Z","shell.execute_reply.started":"2024-06-20T17:38:25.753799Z"},"trusted":true},"outputs":[{"name":"stdout","output_type":"stream","text":["Epoch 1/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 97ms/step - loss: 0.1124 - mae: 0.2437 - val_loss: 0.0053 - val_mae: 0.0648\n","Epoch 2/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 51ms/step - loss: 0.0051 - mae: 0.0563 - val_loss: 0.0048 - val_mae: 0.0593\n","Epoch 3/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 47ms/step - loss: 0.0031 - mae: 0.0406 - val_loss: 0.0025 - val_mae: 0.0432\n","Epoch 4/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 48ms/step - loss: 0.0020 - mae: 0.0333 - val_loss: 0.0019 - val_mae: 0.0361\n","Epoch 5/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 49ms/step - loss: 0.0015 - mae: 0.0285 - val_loss: 0.0014 - val_mae: 0.0297\n","Epoch 6/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 48ms/step - loss: 0.0013 - mae: 0.0255 - val_loss: 0.0011 - val_mae: 0.0269\n","Epoch 7/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 48ms/step - loss: 0.0011 - mae: 0.0242 - val_loss: 0.0011 - val_mae: 0.0271\n","Epoch 8/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 49ms/step - loss: 0.0011 - mae: 0.0244 - val_loss: 0.0012 - val_mae: 0.0285\n","Epoch 9/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 48ms/step - loss: 0.0011 - mae: 0.0246 - val_loss: 0.0013 - val_mae: 0.0287\n","Epoch 10/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 48ms/step - loss: 0.0011 - mae: 0.0240 - val_loss: 0.0012 - val_mae: 0.0277\n","Epoch 11/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 48ms/step - loss: 0.0010 - mae: 0.0233 - val_loss: 0.0011 - val_mae: 0.0270\n","Epoch 12/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 48ms/step - loss: 0.0010 - mae: 0.0229 - val_loss: 0.0011 - val_mae: 0.0264\n","Epoch 13/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 48ms/step - loss: 9.8533e-04 - mae: 0.0226 - val_loss: 0.0010 - val_mae: 0.0259\n","Epoch 14/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 48ms/step - loss: 9.6125e-04 - mae: 0.0223 - val_loss: 0.0010 - val_mae: 0.0253\n","Epoch 15/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 48ms/step - loss: 9.4035e-04 - mae: 0.0221 - val_loss: 9.6782e-04 - val_mae: 0.0249\n","Epoch 16/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 48ms/step - loss: 9.2149e-04 - mae: 0.0218 - val_loss: 9.3528e-04 - val_mae: 0.0244\n","Epoch 17/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 55ms/step - loss: 9.0458e-04 - mae: 0.0216 - val_loss: 9.0525e-04 - val_mae: 0.0240\n","Epoch 18/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 64ms/step - loss: 8.8945e-04 - mae: 0.0214 - val_loss: 8.7729e-04 - val_mae: 0.0236\n","Epoch 19/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 55ms/step - loss: 8.7584e-04 - mae: 0.0212 - val_loss: 8.5052e-04 - val_mae: 0.0232\n","Epoch 20/20\n","\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 51ms/step - loss: 8.6375e-04 - mae: 0.0211 - val_loss: 8.2513e-04 - val_mae: 0.0229\n","\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 164ms/step\n","\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 4.8865e-04 - mae: 0.0169\n","Test Loss: 0.0005475360667333007\n","Test MAE: 0.018060998991131783\n","R2 Score: 0.9174902227784482\n","Mean Squared Error: 0.0005475360082505356\n"]}],"source":["import numpy as np\n","import tensorflow as tf\n","from sklearn.model_selection import train_test_split\n","from sklearn.preprocessing import MinMaxScaler\n","from sklearn.metrics import mean_squared_error, r2_score\n","from tensorflow.keras.models import Sequential\n","from tensorflow.keras.layers import Bidirectional, GRU, Dense\n","from tensorflow.keras.optimizers import Adam\n","from tensorflow.keras.callbacks import EarlyStopping\n","\n","# Normalize the data\n","scaler = MinMaxScaler()\n","df['Close'] = scaler.fit_transform(df[['Close']])\n","\n","# Split the dataset into training and testing sets\n","train_data, test_data = train_test_split(df['Close'], test_size=0.2, shuffle=False, random_state=42)\n","\n","# Prepare input sequences and target values\n","def create_sequences(data, window_size):\n","    X, y = [], []\n","    for i in range(len(data) - window_size):\n","        X.append(data[i:i+window_size])\n","        y.append(data[i+window_size])\n","    return np.array(X), np.array(y)\n","\n","window_size = 30\n","X_train, y_train = create_sequences(train_data.values, window_size)\n","X_test, y_test = create_sequences(test_data.values, window_size)\n","\n","# Reshape input data to include the feature dimension\n","X_train = X_train.reshape(-1, window_size, 1)\n","X_test = X_test.reshape(-1, window_size, 1)\n","\n","# Define the deeper BiGRU model with early stopping\n","model = Sequential([\n","    Bidirectional(GRU(64, return_sequences=True, input_shape=(window_size, 1))),\n","    Bidirectional(GRU(64)),\n","    Dense(32, activation='relu'),\n","    Dense(1)\n","])\n","\n","model.compile(optimizer=Adam(), loss='mse', metrics=['mae'])\n","\n","# Define early stopping criteria\n","early_stopping = EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True)\n","\n","# Train the model with early stopping\n","model.fit(X_train, y_train, epochs=20, batch_size=32, validation_split=0.2, callbacks=[early_stopping])\n","\n","# Predictions\n","y_pred = model.predict(X_test)\n","\n","# Evaluation\n","loss, mae = model.evaluate(X_test, y_test)\n","print('Test Loss:', loss)\n","print('Test MAE:', mae)\n","\n","# Calculate R2 score\n","r2 = r2_score(y_test, y_pred)\n","print('R2 Score:', r2)\n","\n","# Calculate MSE\n","mse = mean_squared_error(y_test, y_pred)\n","print('Mean Squared Error:', mse)"]}],"metadata":{"kaggle":{"accelerator":"none","dataSources":[{"datasetId":4772437,"sourceId":8084907,"sourceType":"datasetVersion"}],"dockerImageVersionId":30732,"isGpuEnabled":false,"isInternetEnabled":true,"language":"python","sourceType":"notebook"},"kernelspec":{"display_name":"Python 3","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":"3.10.13"}},"nbformat":4,"nbformat_minor":4}