Upload 2 files

app.py

@@ -0,0 +1,230 @@
+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=True, show_error=True)
+
+
+
+

requirements.txt

@@ -0,0 +1,6 @@
+catboost==1.1
+gradio==3.15.0
+numpy==1.21.6
+pandas==1.4.2
+scikit_learn==1.2.0
+xgboost==1.6.2