Add files via upload

model.ipynb

@@ -0,0 +1,126 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "R9TP3WqxNLCI"
+      },
+      "outputs": [],
+      "source": [
+        "import tensorflow as tf # for model arc\n",
+        "from tensorflow.keras.models import Sequential\n",
+        "from tensorflow.keras.layers import Dense, LSTM\n",
+        "import pandas as pd # for split dataset\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "import numpy as np # for predict or test the model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Load dataset\n",
+        "url = 'https://raw.githubusercontent.com/carbonzeroapp/carbonzero_ml_model/main/data/datasetKgCO2.csv'\n",
+        "dataset = pd.read_csv(url, delimiter=',', header=0)\n",
+        "\n",
+        "x = dataset.iloc[:,:-1].values\n",
+        "y = dataset.iloc[:,1].values\n",
+        "\n",
+        "# Split dataset into train and validation\n",
+        "x_train, x_val, y_train, y_val = train_test_split(x, y, test_size=0.2, random_state=0)"
+      ],
+      "metadata": {
+        "id": "Jn8tVe8qNqKY"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Model architecture\n",
+        "model = Sequential([\n",
+        "    Dense(64, activation='relu', input_shape=(None, 1)),\n",
+        "    Dense(32, activation='relu'),\n",
+        "    LSTM(4, activation='relu'),\n",
+        "    Dense(32, activation='relu'),\n",
+        "    Dense(4, activation='linear')])\n",
+        "\n",
+        "# Optimizer and loss for the model\n",
+        "model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),\n",
+        "              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
+        "              metrics=['acc'])"
+      ],
+      "metadata": {
+        "id": "CT6JG2tuN7yC"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Training the model\n",
+        "model.fit(tf.expand_dims(x_train, axis=-1), y_train, epochs=100, validation_data=(x_val, y_val), steps_per_epoch=10)"
+      ],
+      "metadata": {
+        "id": "YNyFqgvnONiV"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Dtype input can be int or float\n",
+        "input_data = np.array([[30]])  # Single numerical value as input\n",
+        "\n",
+        "# Make the prediction\n",
+        "prediction = model.predict(input_data)\n",
+        "\n",
+        "# The prediction will be an array of probabilities for each class\n",
+        "# If you have multiple classes, you can retrieve the predicted class with the highest probability\n",
+        "predicted_class = prediction.argmax()\n",
+        "\n",
+        "print(\"Predicted class:\", predicted_class)"
+      ],
+      "metadata": {
+        "id": "fNWPNNXPOoE3"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Note\n",
+        "\n",
+        "# The input is total emission (Kg CO2)\n",
+        "# Emission mean Indonesia for each individu is 42 per week\n",
+        "# The label for class are:\n",
+        "  # '1' stands for 'low' from mean (< 32)\n",
+        "  # '2' stands for 'average' around mean (32 - 52)\n",
+        "  # '3' stands for 'high' from mean (> 52)"
+      ],
+      "metadata": {
+        "id": "_kzN5zJdu48e"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}