pages/3_Training the Model.py

import time
from utils.levels import complete_level, render_page, initialize_level
from utils.login import get_login, initialize_login
import streamlit as st
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import r2_score
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import RandomizedSearchCV
import matplotlib.pyplot as plt
from matplotlib.backends.backend_agg import RendererAgg
_lock = RendererAgg.lock
import base64
from io import BytesIO
from PIL import Image, ImageFilter
import lightgbm as lgb

initialize_login()
initialize_level()

LEVEL = 3

File_PATH = 'datasets/Building_forcasting.csv'

def process_file(csv_file):
    data = pd.read_csv(csv_file, index_col='Timestamp')
    data.index = pd.to_datetime(data.index)
    data = data.fillna(0)
    return data


def model_predict(data, model_choice, train_size, tune_model):
    if model_choice == 'LightGBM':
        model = lgb.LGBMRegressor() if not tune_model else lgb.LGBMRegressor(**tuned_parameters('lgbm'))
    elif model_choice == 'Random Forest':
        model = RandomForestRegressor(n_estimators=100, random_state=42) if not tune_model else RandomForestRegressor(**tuned_parameters('rf'))

    X, y = create_model_inputs(data, 288, 288)

    X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=train_size/100, random_state=42, shuffle=False)

    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)

    return y_test, y_pred, model


def create_model_inputs(data, lag, mean_period):
    df_processed = data.copy()
    df_processed['PV_Output_lag'] = df_processed['PV_Output'].shift(lag)
    df_processed['PV_Output_mean'] = df_processed['PV_Output'].rolling(window=mean_period).mean()

    X = df_processed[['Solar_Irradiance', 'Temperature', 'Rain_Fall', 'Wind_speed', 'PV_Output_lag', 'PV_Output_mean']].dropna()
    y = df_processed[['PV_Output']].loc[X.index]

    return X, y


def show_output(y_test, y_pred):
    st.sidebar.subheader("Model Performance")
    st.sidebar.write(f"Test R2 score: {r2_score(y_test, y_pred):.2f}")

    fig, axs = plt.subplots(3, figsize=(12, 18))
    axs[0].plot(y_test.index, y_pred/1000, label='Predicted')
    axs[0].plot(y_test.index, y_test['PV_Output']/1000, label='Actual')
    axs[0].legend()
    axs[0].set_title('Prediction vs Actual (Solar Power Generation)')
    axs[0].set_xlabel('Date')
    axs[0].set_ylabel('Solar Power Generation (kW)')

    axs[1].plot(y_test.index, y_pred/1000, label='Predicted')
    axs[1].set_title('Predicted Solar Power Generation')
    axs[1].set_xlabel('Date')
    axs[1].set_ylabel('Solar Power Generation (kW)')

    axs[2].plot(y_test.index, y_test['PV_Output']/1000, label='Actual')
    axs[2].set_title('Actual Solar Power Generation')
    axs[2].set_xlabel('Date')
    axs[2].set_ylabel('Solar Power Generation (kW)')

    fig.tight_layout()
    with _lock:
        st.pyplot(fig)

    return fig


def download_link(y_test, y_pred):
    y_pred_df = pd.DataFrame({'Timestamp': y_test.index, 'Predicted_Power': y_pred, 'Actual_Total_Power_(kW)': y_test['PV_Output']})
    csv = y_pred_df.to_csv(index=False)
    b64 = base64.b64encode(csv.encode()).decode()
    href = f'<a href="data:file/csv;base64,{b64}" download="Predicted_Solar_Power.csv">Download Predicted Power CSV File</a>'
    st.sidebar.markdown(href, unsafe_allow_html=True)


def feature_importance_plot(model, feature_names):
    # Get feature importances
    importance = model.feature_importances_
    # Normalize by the sum of all importances
    importance = 100.0 * (importance / importance.sum())
    plt.figure(figsize=(10, 6))
    plt.bar(feature_names, importance)
    plt.title('Feature Importance')
    plt.xlabel('Features')
    plt.ylabel('Importance (%)')
    return plt.gcf()


def download_plot(fig):
    tmpfile = BytesIO()
    fig.savefig(tmpfile, format='png')
    encoded = base64.b64encode(tmpfile.getvalue()).decode('utf-8')

    href = f'<a href="data:image/png;base64,{encoded}" download="plot.png">Download Result Plot</a>'
    st.sidebar.markdown(href, unsafe_allow_html=True)


def tuned_parameters(model):
    if model == 'lgbm':
        params = {
            'num_leaves': [10, 20, 30, 40, 50],
            'max_depth': [-1, 3, 5, 10],
            'learning_rate': [0.01, 0.05, 0.1],
            'n_estimators': [100, 500, 1000]
        }
        return params

    elif model == 'rf':
        params = {
            'n_estimators': [10, 100, 500, 1000],
            'max_depth': [None, 10, 20, 30, 40, 50],
            'min_samples_split': [2, 5, 10],
            'min_samples_leaf': [1, 2, 4]
        }
        return params

def step3_page():
    st.header("Training the Model")
    st.subheader("Step 1: Data Collection")
    st.write("To initiate the weather forecasting model training process, kindly provide a sufficient and relevant dataset with weather-related attributes in .csv format for uploading. This dataset will be crucial for the model's training and accuracy.")
    # Display the image and information in a grid layout
    # if st.button("Upload"):
    col1 = st.columns([1])
    with col1[0]:
        csv_file = st.file_uploader("Upload CSV", type=['csv'])
        if csv_file is not None:
            data = process_file(csv_file)
            df = pd.DataFrame(data)
            st.subheader("Let's display the uploaded dataset!")
            st.dataframe(df)
        else:
            st.error("Please upload a valid .csv file")

    # st.subheader("Step 2: Data Preprocessing and Feature Engineering")
    # st.write("Now let's preprocess our dataset to handle missing values, outliers and inconsistencies and then perform feature engineering tasks to extract meaningful features from the raw data. Finally we need to separate training variables (X) and target variable (y).")
    # if st.button("Create Features and Target variable"):
    #     X, y = create_model_inputs(data, 288, 288)
    #     col1, col2 = st.columns([2])
    #     with col1:
    #         st.subheader("Let's display the Features!")
    #         st.dataframe(X)
    #     with col2:
    #         st.subheader("Let's display our Target variable")
    #         st.dataframe(y)
    #
    # st.subheader("Step 3: Data Splitting")
    # st.write(
    #     "Now let's split into training and testing sets. The training set is used to train the machine learning model, and the testing set is used to evaluate its performance.")
    # if st.button("Create Features and Target variable"):
        # train_size = st.sidebar.slider("Select Train Dataset Size (%)", min_value=10, max_value=90, value=70)
        #
        # models = ['LightGBM', 'Random Forest']
        # model_choice = st.sidebar.selectbox('Choose Model', models)
        #
        # tune_model = st.sidebar.checkbox('Tune Hyperparameters')
        #
        # y_test, y_pred, model = model_predict(data, model_choice, train_size, tune_model)
        #
        # # Display feature importance
        # if st.sidebar.checkbox('Show feature importance'):
        #     feature_names = ['Solar_Irradiance', 'Temperature', 'Rain_Fall', 'Wind_speed', 'PV_Output_lag',
        #                      'PV_Output_mean']
        #     fig = feature_importance_plot(model, feature_names)
        #     with _lock:
        #         st.pyplot(fig)
        #
        # fig = show_output(y_test, y_pred)
        #
        # download_link(y_test, y_pred)
        #
        # download_plot(fig)


    if st.button("Complete"):
        complete_level(LEVEL)


render_page(step3_page, LEVEL)