Spaces:
Sleeping
Sleeping
File size: 9,960 Bytes
92e31e2 b636878 92e31e2 b636878 92e31e2 b636878 92e31e2 e764c4e 92e31e2 8fa1dcd b73615c 8fa1dcd b73615c 8fa1dcd b73615c 8fa1dcd b73615c aa539b7 b73615c aa539b7 d96d140 b73615c d96d140 b73615c d96d140 9708914 b636878 9708914 b636878 d96d140 b636878 92e31e2 78571a1 735aaf0 92e31e2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 |
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_train(train_X, train_y, 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_train, X_test, y_train, y_test = train_test_split(train_X, train_y, train_size=train_size/100, random_state=42, shuffle=False)
model.fit(X_train, y_train)
return model, X_test, y_test
def model_predict(model, X_test, y_test):
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_train, X_test, y_train, y_test = train_test_split(train_X, train_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"):
state = "data collection"
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.info("Let's display the uploaded dataset!")
st.dataframe(df)
state = "preprocessing"
else:
st.error("Please upload a valid .csv file")
if state == "preprocessing":
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)
cols = st.columns(2)
state = "splitting"
with cols[0]:
st.info("Let's display the Features!")
st.dataframe(X)
with cols[1]:
st.info("Let's display our Target variable")
st.dataframe(y)
else:
pass
if state == "splitting":
st.subheader("Step 3: Data Splitting")
st.write("Now let's split the dataset 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. For that, you have to select the train-test split %.")
train_size = st.slider("Select Train Dataset Size (%)", min_value=10, max_value=90, value=70)
state = "model selection"
else:
pass
if state == "model selection":
st.subheader("Step 4: Model Selection")
st.write("Different machine learning algorithms can be used for weather forecasting and the choice of model depends on the characteristics of the data and the forecasting task. But for this tutorial, you can select between a 'LightGBM' model and a 'Random Forest' model.")
models = ['LightGBM', 'Random Forest']
model_choice = st.selectbox('Choose Model', models)
state = "model training"
else:
pass
if state == "model training":
st.subheader("Step 5: Model Training")
st.write("Finally, let;s train our weather forecasting model based on the parameters that you have selected!")
tune_model = st.checkbox('Tune Hyperparameters')
if st.button("Train", key="train"):
model, X_test, y_test = model_train(X, y, model_choice, train_size, tune_model)
my_bar = st.progress(0, text="Training model...")
for i in range(100):
my_bar.progress(i, text="Training model...")
my_bar.progress(100, text="Training completed")
state = "model predict"
else:
pass
# 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)
|