Spaces:
Build error
Build error
File size: 10,772 Bytes
7c53ece aeacb2a 7c53ece |
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 |
import numpy as np
from sklearn.linear_model import LinearRegression
import gradio as gr
from sklearn.model_selection import train_test_split
from sklearn.ensemble import AdaBoostRegressor, ExtraTreesRegressor
import pandas as pd
from sklearn.tree import DecisionTreeRegressor, ExtraTreeRegressor
from xgboost import XGBRegressor
from sklearn.metrics import r2_score
from catboost import CatBoostRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import r2_score
import random
logger = gr.SimpleCSVLogger()
# set all random seeds to 42
random.seed(42)
np.random.seed(42)
def AdaBoostRegressorR2(x_file_obj,y_file_obj,learning_rate, n_estimators, loss, base_estimator, test_size,random_seed):
if base_estimator == "DecisionTreeRegressor":
base_estimator = DecisionTreeRegressor()
elif base_estimator == "XGBoost":
base_estimator = XGBRegressor()
elif base_estimator == "RandomForestRegressor":
base_estimator = RandomForestRegressor()
elif base_estimator == "CatBoostRegressor":
base_estimator = CatBoostRegressor()
elif base_estimator == "LinearRegression":
base_estimator = LinearRegression()
elif base_estimator == "ExtraTreeRegressor":
base_estimator = ExtraTreeRegressor()
elif base_estimator == "None":
base_estimator = None
X = pd.read_csv(x_file_obj.name,dtype=str)
y = pd.read_csv(y_file_obj.name,dtype=str)
y = y.values.ravel()
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=random_seed)
model = AdaBoostRegressor(learning_rate=learning_rate, n_estimators=n_estimators, loss=loss,base_estimator=base_estimator,random_state=random_seed)
model.fit(x_train, y_train)
predictions = model.predict(x_test)
return r2_score(y_test, predictions)
adaInterface = gr.Interface(
AdaBoostRegressorR2,
[
gr.components.File(label="X File (CSV)"),
gr.components.File(label="Y File (CSV)"),
gr.components.Slider(0.1, 1, default=0.1, label="learning_rate"),
gr.components.Slider(0, 1000, default=10, label="n_estimators"),
gr.components.Dropdown(["linear", "square", "exponential"], label="loss"),
gr.components.Dropdown(["DecisionTreeRegressor","XGBoost","RandomForestRegressor","CatBoostRegressor","LinearRegression","ExtraTreeRegressor","None"], label="base_estimator"),
gr.components.Slider(0.1, 0.9, default=0.2, label="test_size"),
gr.components.Slider(0, 100, default=42, label="random_seed")
],
outputs="number",
title="AdaBoostRegressor",
description="Treino de um modelo de regressão com AdaBoostRegressor",
allow_flagging="manual"
)
def CatBoostRegressorR2(x_file_obj,y_file_obj,learning_rate, n_estimators, loss, max_depth, max_bin, l2_leaf_reg, test_size,random_seed):
X = pd.read_csv(x_file_obj.name,dtype=str)
y = pd.read_csv(y_file_obj.name,dtype=str)
y = y.values.ravel()
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=random_seed)
model = CatBoostRegressor(learning_rate=learning_rate, n_estimators=n_estimators, loss_function=loss,max_depth=max_depth,
max_bin=max_bin,l2_leaf_reg=l2_leaf_reg ,random_state=random_seed)
model.fit(x_train, y_train)
predictions = model.predict(x_test)
return r2_score(y_test, predictions)
catInterface = gr.Interface(
CatBoostRegressorR2,
[
gr.components.File(label="X File (CSV)"),
gr.components.File(label="Y File (CSV)"),
gr.components.Slider(0.1, 1, default=0.1, label="learning_rate"),
gr.components.Slider(0, 1000, default=10, label="n_estimators"),
gr.components.Dropdown(["RMSE", "MAE", "Quantile:alpha=0.9", "LogLinQuantile:alpha=0.9", "Poisson", "MAPE", "MultiRMSE","Quantile", "LogLinQuantile", "Lq:q=1", "Lq:q=2"], label="loss"),
gr.components.Slider(0, 100, default=1, label="max_depth"),
gr.components.Slider(1, 255, default=255, label="max_bin"),
gr.components.Slider(0, 100, default=3, label="l2_leaf_reg"),
gr.components.Slider(0.1, 0.9, default=0.2, label="test_size"),
gr.components.Slider(0, 100, default=42, label="random_seed")
],
outputs="number",
title="CatBoostRegressor",
description="Treino de um modelo de regressão com CatBoostRegressor",
allow_flagging="manual"
)
def RandomForestRegressorR2(x_file_obj,y_file_obj,n_estimators,
criterion, max_depth,min_samples_split,
min_samples_leaf,min_weight_fraction_leaf,max_features,max_leaf_nodes,min_impurity_decrease,bootstrap,n_jobs,test_size,random_seed):
max_depth = int(max_depth)
X = pd.read_csv(x_file_obj.name,dtype=str)
y = pd.read_csv(y_file_obj.name,dtype=str)
y = y.values.ravel()
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=random_seed)
model = RandomForestRegressor(n_estimators=n_estimators, criterion=criterion, max_depth=max_depth,
min_samples_split=min_samples_split,min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,max_features=max_features,max_leaf_nodes=max_leaf_nodes,
min_impurity_decrease=min_impurity_decrease,bootstrap=bootstrap,n_jobs=n_jobs,random_state=random_seed)
model.fit(x_train, y_train)
predictions = model.predict(x_test)
return r2_score(y_test, predictions)
randomForestInterface = gr.Interface(
RandomForestRegressorR2,
[
gr.components.File(label="X File (CSV)"),
gr.components.File(label="Y File (CSV)"),
gr.components.Slider(0, 1000, default=10, label="n_estimators"),
gr.components.Dropdown(["mse", "mae","poisson"], label="criterion",default="mse"),
gr.components.Slider(0, 100, default=1, label="max_depth"),
gr.components.Slider(0, 100, default=1, label="min_samples_split"),
gr.components.Slider(0, 100, default=1, label="min_samples_leaf"),
gr.components.Slider(0, 0.5, default=0, label="min_weight_fraction_leaf"),
gr.components.Dropdown(["auto", "sqrt", "log2"], label="max_features",default="auto"),
gr.components.Slider(0, 100, default=1, label="max_leaf_nodes"),
gr.components.Slider(0, 1, default=0, label="min_impurity_decrease"),
gr.components.Dropdown(["True", "False"], label="bootstrap",default="True"),
gr.components.Dropdown([i for i in range(-1,5,1)], default=-1, label="n_jobs"),
gr.components.Slider(0.1, 0.9, default=0.2, label="test_size"),
gr.components.Slider(0, 100, default=42, label="random_seed")
],
outputs="number",
title="RandomForestRegressor",
description="Treino de um modelo de regressão com RandomForestRegressor",
allow_flagging="manual"
)
# TODO - Add more parameters EXTRA TREE
def ExtraTreesRegressorR2(x_file_obj,y_file_obj,n_estimators,
criterion, max_depth,min_samples_split,
min_samples_leaf,min_weight_fraction_leaf,max_features,max_leaf_nodes,min_impurity_decrease,bootstrap,n_jobs,test_size,random_seed):
max_depth = int(max_depth)
X = pd.read_csv(x_file_obj.name,dtype=str)
y = pd.read_csv(y_file_obj.name,dtype=str)
y = y.values.ravel()
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=random_seed)
model = ExtraTreesRegressor(n_estimators=n_estimators, criterion=criterion, max_depth=max_depth,
min_samples_split=min_samples_split,min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,max_features=max_features,max_leaf_nodes=max_leaf_nodes,
min_impurity_decrease=min_impurity_decrease,bootstrap=bootstrap,n_jobs=n_jobs,random_state=random_seed)
model.fit(x_train, y_train)
predictions = model.predict(x_test)
return r2_score(y_test, predictions)
extraTreesInterface = gr.Interface(
ExtraTreesRegressorR2,
[
gr.components.File(label="X File (CSV)"),
gr.components.File(label="Y File (CSV)"),
gr.components.Slider(0, 1000, default=10, label="n_estimators"),
gr.components.Dropdown(["mse", "mae","poisson"], label="criterion",default="mse"),
gr.components.Slider(0, 100, default=1, label="max_depth"),
gr.components.Slider(0, 100, default=1, label="min_samples_split"),
gr.components.Slider(0, 100, default=1, label="min_samples_leaf"),
gr.components.Slider(0, 0.5, default=0, label="min_weight_fraction_leaf"),
gr.components.Dropdown(["auto", "sqrt", "log2"], label="max_features",default="auto"),
gr.components.Slider(0, 100, default=1, label="max_leaf_nodes"),
gr.components.Slider(0, 1, default=0, label="min_impurity_decrease"),
gr.components.Dropdown(["True", "False"], label="bootstrap",default="True"),
gr.components.Dropdown([i for i in range(-1,5,1)], default=-1, label="n_jobs"),
gr.components.Slider(0.1, 0.9, default=0.2, label="test_size"),
gr.components.Slider(0, 100, default=42, label="random_seed")
],
outputs="number",
title="ExtraTreesRegressor",
description="Treino de um modelo de regressão com ExtraTreesRegressor",
allow_flagging="manual"
)
def linearRegressionR2(x_file_obj,y_file_obj,fit_intercept, normalize, copy_X):
X = pd.read_csv(x_file_obj.name,dtype=str)
y = pd.read_csv(y_file_obj.name,dtype=str)
y = y.values.ravel()
x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
model = LinearRegression(fit_intercept=fit_intercept, normalize=normalize, copy_X=copy_X)
model.fit(x_train, y_train)
predictions = model.predict(x_test)
return r2_score(y_test, predictions)
linearRegressionInterface = gr.Interface(
linearRegressionR2,
[
gr.components.File(label="X File (CSV)"),
gr.components.File(label="Y File (CSV)"),
gr.components.Checkbox(True, label="fit_intercept"),
gr.components.Checkbox(False, label="normalize"),
gr.components.Checkbox(True, label="copy_X"),
],
outputs="number",
title="LinearRegression",
description="Treino de um modelo de regressão com LinearRegression",
allow_flagging="manual")
iface = gr.TabbedInterface([catInterface, adaInterface, randomForestInterface, extraTreesInterface, linearRegressionInterface],
["CatBoostRegressor", "AdaBoostRegresssor","RandomForestRegressor", "ExtraTreesRegressor","LinearRegression"],theme="dark")
iface.launch(share=False, show_error=True)
|