series_time.ipynb

series_time.ipynb

@@ -0,0 +1,154 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import streamlit as st\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "# Cargar los datos de los dos CSV\n",
+    "file1 = 'PARCIAL-AGUA-_2_.csv'\n",
+    "file2 = 'PARCIAL-AGUA-_3_.csv'\n",
+    "\n",
+    "data1 = pd.read_csv(file1)\n",
+    "data2 = pd.read_csv(file2)\n",
+    "\n",
+    "# Convertir la columna 'FECHA' a objetos datetime y filtrar por años\n",
+    "data1['FECHA'] = pd.to_datetime(data1['FECHA'])\n",
+    "data2['FECHA'] = pd.to_datetime(data2['FECHA'])\n",
+    "\n",
+    "filtered_data1 = data1[data1['FECHA'].dt.year >= 2007]\n",
+    "filtered_data2 = data2[data2['FECHA'].dt.year >= 2007]\n",
+    "\n",
+    "# Combinar los valores de ambos conjuntos de datos\n",
+    "combined_values = np.concatenate([filtered_data1['VALOR-LS-CF-N'].values, filtered_data2['VALOR-LS-CF-N'].values]).reshape(-1, 1)\n",
+    "\n",
+    "# Seleccionar la variable objetivo y escalar los valores\n",
+    "scaler = MinMaxScaler()\n",
+    "scaled_values = scaler.fit_transform(combined_values)\n",
+    "\n",
+    "# Dividir los datos escalados en los conjuntos de datos originales\n",
+    "scaled_values1 = scaled_values[:len(filtered_data1)]\n",
+    "scaled_values2 = scaled_values[len(filtered_data1):]\n",
+    "\n",
+    "# Función para crear ventanas deslizantes\n",
+    "def sliding_windows(data, seq_length):\n",
+    "    x, y = [], []\n",
+    "    for i in range(len(data) - seq_length):\n",
+    "        x.append(data[i:i + seq_length])\n",
+    "        y.append(data[i + seq_length])\n",
+    "    return np.array(x), np.array(y)\n",
+    "\n",
+    "# Preparar las ventanas deslizantes para cada conjunto de datos\n",
+    "seq_length = 4\n",
+    "x_train, y_train = sliding_windows(scaled_values1, seq_length)\n",
+    "x_test, y_test = sliding_windows(scaled_values2, seq_length)\n",
+    "\n",
+    "# Convertir a tensores de PyTorch\n",
+    "trainX = torch.Tensor(x_train)\n",
+    "trainY = torch.Tensor(y_train)\n",
+    "testX = torch.Tensor(x_test)\n",
+    "testY = torch.Tensor(y_test)\n",
+    "\n",
+    "# Definir el modelo LSTM\n",
+    "class LSTM(nn.Module):\n",
+    "    def __init__(self, input_size, hidden_size, num_layers, output_size):\n",
+    "        super(LSTM, self).__init__()\n",
+    "        self.hidden_size = hidden_size\n",
+    "        self.num_layers = num_layers\n",
+    "        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)\n",
+    "        self.fc = nn.Linear(hidden_size, output_size)\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size)\n",
+    "        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size)\n",
+    "        out, _ = self.lstm(x, (h0, c0))\n",
+    "        out = self.fc(out[:, -1, :])\n",
+    "        return out\n",
+    "\n",
+    "# Aquí puedes definir otros modelos si lo deseas\n",
+    "# ...\n",
+    "\n",
+    "# Interfaz de Streamlit\n",
+    "st.title('Predicción de Series de Tiempo')\n",
+    "st.sidebar.title('Parámetros del Modelo')\n",
+    "\n",
+    "model_type = st.sidebar.selectbox('Selecciona el modelo', ('LSTM', 'Otro Modelo'))\n",
+    "num_epochs = st.sidebar.slider('Número de épocas', 100, 500, 200)\n",
+    "learning_rate = st.sidebar.number_input('Tasa de aprendizaje', 0.001, 0.1, 0.01, 0.001)\n",
+    "\n",
+    "if model_type == 'LSTM':\n",
+    "    input_size = 1\n",
+    "    hidden_size = 50\n",
+    "    num_layers = 2\n",
+    "    output_size = 1\n",
+    "\n",
+    "    model = LSTM(input_size, hidden_size, num_layers, output_size)\n",
+    "\n",
+    "    criterion = nn.MSELoss()\n",
+    "    optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)\n",
+    "\n",
+    "    if st.sidebar.button('Entrenar y Predecir'):\n",
+    "        for epoch in range(num_epochs):\n",
+    "            model.train()\n",
+    "            outputs = model(trainX)\n",
+    "            optimizer.zero_grad()\n",
+    "            loss = criterion(outputs, trainY)\n",
+    "            loss.backward()\n",
+    "            optimizer.step()\n",
+    "            if (epoch+1) % 100 == 0:\n",
+    "                st.write(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')\n",
+    "\n",
+    "        model.eval()\n",
+    "        train_predict = model(trainX)\n",
+    "        test_predict = model(testX)\n",
+    "\n",
+    "        train_predict = scaler.inverse_transform(train_predict.detach().numpy().reshape(-1, 1))\n",
+    "        trainY_plot = scaler.inverse_transform(trainY.numpy().reshape(-1, 1))\n",
+    "        test_predict = scaler.inverse_transform(test_predict.detach().numpy().reshape(-1, 1))\n",
+    "        testY_plot = scaler.inverse_transform(testY.numpy().reshape(-1, 1))\n",
+    "\n",
+    "        fig, ax = plt.subplots(figsize=(12, 6))\n",
+    "        ax.plot(filtered_data1['FECHA'].values[seq_length:seq_length+len(trainY)], trainY_plot, label='Datos de entrenamiento')\n",
+    "        ax.plot(filtered_data1['FECHA'].values[seq_length:seq_length+len(trainY)], train_predict, label='Predicciones de entrenamiento')\n",
+    "        ax.plot(filtered_data2['FECHA'].values[seq_length:seq_length+len(testY)], testY_plot, label='Datos de prueba')\n",
+    "        ax.plot(filtered_data2['FECHA'].values[seq_length:seq_length+len(testY)], test_predict, label='Predicciones de prueba')\n",
+    "        ax.set_xlabel('Fecha')\n",
+    "        ax.set_ylabel('VALOR-LS-CF-N')\n",
+    "        ax.set_title('Predicciones con LSTM')\n",
+    "        ax.legend()\n",
+    "        ax.grid(True)\n",
+    "        st.pyplot(fig)"
+   ]
+  }
+ ],
+ "metadata": {
+  "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": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}