Spaces:
Sleeping
Sleeping
File size: 12,789 Bytes
0ecc8d7 905c0d8 0ecc8d7 905c0d8 0ecc8d7 905c0d8 0ecc8d7 a964dbc 0ecc8d7 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 |
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.impute import SimpleImputer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression, Ridge, Lasso, ElasticNet, LogisticRegression
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor
from sklearn.svm import SVR
from xgboost import XGBRegressor
from lightgbm import LGBMRegressor
from sklearn.metrics import mean_squared_error, r2_score
import streamlit as st
class RegressionModels:
def __init__(self):
self.data = None
self.X_train = None
self.X_test = None
self.y_train = None
self.y_test = None
self.column_transformer = None # Initialize as None
self.models = {
'Linear Regression': LinearRegression(),
'Polynomial Regression': LinearRegression(),
'Ridge Regression': Ridge(),
'Lasso Regression': Lasso(),
'ElasticNet Regression': ElasticNet(),
'Logistic Regression': LogisticRegression(),
'Decision Tree Regression': DecisionTreeRegressor(),
'Random Forest Regression': RandomForestRegressor(),
'Gradient Boosting Regression': GradientBoostingRegressor(),
'Support Vector Regression (SVR)': SVR(),
'XGBoost': XGBRegressor(),
'LightGBM': LGBMRegressor()
}
def add_data(self, X, y):
self.data = (X, y)
def split_data(self, test_size=0.2, random_state=None):
if self.data is None:
raise ValueError("No data provided. Use add_data method to add data first.")
X, y = self.data
self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(X, y, test_size=test_size, random_state=random_state)
def build_preprocessor(self):
if self.column_transformer is not None:
return self.column_transformer # Return the existing fitted ColumnTransformer
else:
# Separate numerical and categorical columns
numeric_features = self.X_train.select_dtypes(include=['int64', 'float64']).columns
categorical_features = self.X_train.select_dtypes(include=['object']).columns
# Define transformers for numerical and categorical data
numeric_transformer = Pipeline(steps=[
('imputer', SimpleImputer(strategy='mean')),
('scaler', StandardScaler())
])
categorical_transformer = Pipeline(steps=[
('imputer', SimpleImputer(strategy='most_frequent')),
('onehot', OneHotEncoder(handle_unknown='ignore'))
])
# Combine transformers using ColumnTransformer
self.column_transformer = ColumnTransformer(
transformers=[
('num', numeric_transformer, numeric_features),
('cat', categorical_transformer, categorical_features)
])
return self.column_transformer
def fit(self, model_name):
if self.X_train is None or self.y_train is None:
raise ValueError("Data not split. Use split_data method to split data into training and testing sets.")
model = self.models[model_name]
preprocessor = self.build_preprocessor()
model_pipeline = Pipeline(steps=[
('preprocessor', preprocessor),
('model', model)
])
model_pipeline.fit(self.X_train, self.y_train)
def train(self, model_name):
if self.X_train is None or self.y_train is None or self.X_test is None:
raise ValueError("Data not split. Use split_data method to split data into training and testing sets.")
model = self.models[model_name]
preprocessor = self.build_preprocessor()
model_pipeline = Pipeline(steps=[
('preprocessor', preprocessor),
('model', model)
])
model_pipeline.fit(self.X_train, self.y_train)
y_pred = model_pipeline.predict(self.X_test)
return y_pred
def evaluate(self, model_name):
if self.X_test is None or self.y_test is None:
raise ValueError("Data not split. Use split_data method to split data into training and testing sets.")
model = self.models[model_name]
preprocessor = self.build_preprocessor()
model_pipeline = Pipeline(steps=[
('preprocessor', preprocessor),
('model', model)
])
model_pipeline.fit(self.X_train, self.y_train)
y_pred = model_pipeline.predict(self.X_test)
mse = mean_squared_error(self.y_test, y_pred)
r2 = r2_score(self.y_test, y_pred)
return mse, r2
def predict(self, model_name, X):
model = self.models[model_name]
preprocessor = self.build_preprocessor() # Ensure that the ColumnTransformer is fitted
model_pipeline = Pipeline(steps=[
('preprocessor', preprocessor),
('model', model)
])
return model_pipeline.predict(X)
'''
class RegressionModels:
def __init__(self):
self.data = None
self.X_train = None
self.X_test = None
self.y_train = None
self.y_test = None
self.models = {
'Linear Regression': LinearRegression(),
'Polynomial Regression': LinearRegression(),
'Ridge Regression': Ridge(),
'Lasso Regression': Lasso(),
'ElasticNet Regression': ElasticNet(),
'Logistic Regression': LogisticRegression(),
'Decision Tree Regression': DecisionTreeRegressor(),
'Random Forest Regression': RandomForestRegressor(),
'Gradient Boosting Regression': GradientBoostingRegressor(),
'Support Vector Regression (SVR)': SVR(),
'XGBoost': XGBRegressor(),
'LightGBM': LGBMRegressor()
}
def add_data(self, X, y):
self.data = (X, y)
def split_data(self, test_size=0.2, random_state=None):
if self.data is None:
raise ValueError("No data provided. Use add_data method to add data first.")
X, y = self.data
self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(X, y, test_size=test_size, random_state=random_state)
def build_preprocessor(self):
# Separate numerical and categorical columns
numeric_features = self.X_train.select_dtypes(include=['int64', 'float64']).columns
categorical_features = self.X_train.select_dtypes(include=['object']).columns
# Define transformers for numerical and categorical data
numeric_transformer = Pipeline(steps=[
('imputer', SimpleImputer(strategy='mean')),
('scaler', StandardScaler())
])
categorical_transformer = Pipeline(steps=[
('imputer', SimpleImputer(strategy='most_frequent')),
('onehot', OneHotEncoder(handle_unknown='ignore'))
])
# Combine transformers using ColumnTransformer
preprocessor = ColumnTransformer(
transformers=[
('num', numeric_transformer, numeric_features),
('cat', categorical_transformer, categorical_features)
])
return preprocessor
def fit(self, model_name):
if self.X_train is None or self.y_train is None:
raise ValueError("Data not split. Use split_data method to split data into training and testing sets.")
model = self.models[model_name]
preprocessor = self.build_preprocessor()
model_pipeline = Pipeline(steps=[
('preprocessor', preprocessor),
('model', model)
])
model_pipeline.fit(self.X_train, self.y_train)
def train(self, model_name):
if self.X_train is None or self.y_train is None or self.X_test is None:
raise ValueError("Data not split. Use split_data method to split data into training and testing sets.")
model = self.models[model_name]
preprocessor = self.build_preprocessor()
model_pipeline = Pipeline(steps=[
('preprocessor', preprocessor),
('model', model)
])
model_pipeline.fit(self.X_train, self.y_train)
y_pred = model_pipeline.predict(self.X_test)
return y_pred
def evaluate(self, model_name):
if self.X_test is None or self.y_test is None:
raise ValueError("Data not split. Use split_data method to split data into training and testing sets.")
model = self.models[model_name]
preprocessor = self.build_preprocessor()
model_pipeline = Pipeline(steps=[
('preprocessor', preprocessor),
('model', model)
])
model_pipeline.fit(self.X_train, self.y_train)
y_pred = model_pipeline.predict(self.X_test)
mse = mean_squared_error(self.y_test, y_pred)
r2 = r2_score(self.y_test, y_pred)
return mse, r2
def predict(self, model_name, X):
model = self.models[model_name]
preprocessor = self.build_preprocessor()
model_pipeline = Pipeline(steps=[
('preprocessor', preprocessor),
('model', model)
])
st.write("Model", model)
st.write(X.head(4))
return model_pipeline.predict(X)
'''
'''
from sklearn.linear_model import LinearRegression, Ridge, Lasso, ElasticNet, LogisticRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor
from sklearn.svm import SVR
from xgboost import XGBRegressor
from lightgbm import LGBMRegressor
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.model_selection import train_test_split
from sklearn.model_selection import train_test_split
from xgboost import XGBRegressor
from lightgbm import LGBMRegressor
class RegressionModels:
def __init__(self):
self.data = None
self.X_train = None
self.X_test = None
self.y_train = None
self.y_test = None
self.models = {
'Linear Regression': LinearRegression(),
'Polynomial Regression': LinearRegression(),
'Ridge Regression': Ridge(),
'Lasso Regression': Lasso(),
'ElasticNet Regression': ElasticNet(),
'Logistic Regression': LogisticRegression(),
'Decision Tree Regression': DecisionTreeRegressor(),
'Random Forest Regression': RandomForestRegressor(),
'Gradient Boosting Regression': GradientBoostingRegressor(),
'Support Vector Regression (SVR)': SVR(),
'XGBoost': XGBRegressor(),
'LightGBM': LGBMRegressor()
}
def add_data(self, X, y):
self.data = (X, y)
def split_data(self, test_size=0.2, random_state=None):
if self.data is None:
raise ValueError("No data provided. Use add_data method to add data first.")
X, y = self.data
self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(X, y, test_size=test_size, random_state=random_state)
def fit(self, model_name):
if self.X_train is None or self.y_train is None:
raise ValueError("Data not split. Use split_data method to split data into training and testing sets.")
model = self.models[model_name]
model.fit(self.X_train, self.y_train)
def train(self, model_name):
if self.X_train is None or self.y_train is None or self.X_test is None:
raise ValueError("Data not split. Use split_data method to split data into training and testing sets.")
model = self.models[model_name]
model.fit(self.X_train, self.y_train)
y_pred = model.predict(self.X_test)
return y_pred
def evaluate(self, model_name):
if self.X_test is None or self.y_test is None:
raise ValueError("Data not split. Use split_data method to split data into training and testing sets.")
model = self.models[model_name]
y_pred = model.predict(self.X_test)
mse = mean_squared_error(self.y_test, y_pred)
r2 = r2_score(self.y_test, y_pred)
return mse, r2
def predict(self, model_name, X):
model = self.models[model_name]
return model.predict(X)
''' |