{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "gpuType": "T4" }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "accelerator": "GPU" }, "cells": [ { "cell_type": "code", "execution_count": 3, "metadata": { "id": "wr5jRSzXqWsi" }, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd\n", "from sklearn.preprocessing import MinMaxScaler\n", "from tensorflow.keras.models import Sequential\n", "from tensorflow.keras.layers import GRU, Dense\n", "from tensorflow.keras.optimizers import Adam" ] }, { "cell_type": "code", "source": [ "df = pd.read_csv('/content/data.csv', parse_dates=['Date'], index_col='Date')\n", "print(df.head())" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "birFLs17qYSc", "outputId": "fa232ba5-e75c-40c2-e755-d21266156057" }, "execution_count": 4, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ " Temperature\n", "Date \n", "2010-01-01 27.483571\n", "2010-01-02 24.308678\n", "2010-01-03 28.238443\n", "2010-01-04 32.615149\n", "2010-01-05 23.829233\n" ] } ] }, { "cell_type": "code", "source": [ "scaler = MinMaxScaler(feature_range=(0, 1))\n", "scaled_data = scaler.fit_transform(df.values)" ], "metadata": { "id": "jCsekEDrqYVL" }, "execution_count": 5, "outputs": [] }, { "cell_type": "code", "source": [ "def create_dataset(data, time_step=1):\n", " X, y = [], []\n", " for i in range(len(data) - time_step - 1):\n", " X.append(data[i:(i + time_step), 0])\n", " y.append(data[i + time_step, 0])\n", " return np.array(X), np.array(y)\n", "\n", "\n", "time_step = 100\n", "X, y = create_dataset(scaled_data, time_step)\n", "X = X.reshape(X.shape[0], X.shape[1], 1)" ], "metadata": { "id": "NkQ2BeQyqYX0" }, "execution_count": 6, "outputs": [] }, { "cell_type": "code", "source": [ "model = Sequential()\n", "model.add(GRU(units=50, return_sequences=True, input_shape=(X.shape[1], 1)))\n", "model.add(GRU(units=50))\n", "model.add(Dense(units=1))\n", "model.compile(optimizer=Adam(learning_rate=0.001), loss='mean_squared_error')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "K3srfhweqYaD", "outputId": "30c107c2-cbef-4a8c-e85b-7f0684a0b888" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.12/dist-packages/keras/src/layers/rnn/rnn.py:199: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", " super().__init__(**kwargs)\n" ] } ] }, { "cell_type": "code", "source": [ "model.fit(X, y, epochs=10, batch_size=32)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "AxS9I_zTqYcn", "outputId": "727d2929-a255-4949-97bb-90067d06a05d" }, "execution_count": 8, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Epoch 1/10\n", "\u001b[1m247/247\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 16ms/step - loss: 0.0208\n", "Epoch 2/10\n", "\u001b[1m247/247\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 11ms/step - loss: 0.0181\n", "Epoch 3/10\n", "\u001b[1m247/247\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 11ms/step - loss: 0.0180\n", "Epoch 4/10\n", "\u001b[1m247/247\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 11ms/step - loss: 0.0180\n", "Epoch 5/10\n", "\u001b[1m247/247\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 10ms/step - loss: 0.0179\n", "Epoch 6/10\n", "\u001b[1m247/247\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 18ms/step - loss: 0.0177\n", "Epoch 7/10\n", "\u001b[1m247/247\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 13ms/step - loss: 0.0178\n", "Epoch 8/10\n", "\u001b[1m247/247\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 11ms/step - loss: 0.0177\n", "Epoch 9/10\n", "\u001b[1m247/247\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 10ms/step - loss: 0.0179\n", "Epoch 10/10\n", "\u001b[1m247/247\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 10ms/step - loss: 0.0177\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": {}, "execution_count": 8 } ] }, { "cell_type": "code", "source": [ "input_sequence = scaled_data[-time_step:].reshape(1, time_step, 1)\n", "predicted_values = model.predict(input_sequence)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "WerdAcaYqYe-", "outputId": "916b99b8-c5cc-4a10-eda3-e35f37c261b8" }, "execution_count": 9, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 157ms/step\n" ] } ] }, { "cell_type": "code", "source": [ "predicted_values = scaler.inverse_transform(predicted_values)\n", "print(\n", " f\"The predicted temperature for the next day is: {predicted_values[0][0]:.2f}°C\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "ET65CITAqYhk", "outputId": "3bc4b738-56fe-4915-b536-dfcadb1251c1" }, "execution_count": 10, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "The predicted temperature for the next day is: 24.50°C\n" ] } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "Qs1TWhDOqYkE" }, "execution_count": 8, "outputs": [] } ] }