File size: 7,798 Bytes
68fbecb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder, OrdinalEncoder
from sklearn.linear_model import LinearRegression, LogisticRegression
from sklearn.ensemble import GradientBoostingClassifier, RandomForestRegressor,HistGradientBoostingRegressor
#import xgboost
from sklearn.compose import ColumnTransformer
#import pickle
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, r2_score
import streamlit as st
import time
#import shap
#import matplotlib as mt

def train(data=None,problem="Regression",model="LinearRegression",label=None):

    df = pd.read_csv(data)

    target = df[label].copy()
    features = df.drop(label, axis=1)

    X_train,X_test,y_train,y_test = train_test_split(features,target,test_size=0.20,random_state=42,shuffle=True)

    num_features = []
    cat_features = []
    cols = list(features.columns)
    for i in cols:
        if df[i].dtypes == "object":
            cat_features.append(i)
        else:
            num_features.append(i)

    if problem == "Regression":
        trf = ColumnTransformer([("num_trf",StandardScaler(),num_features),
                                 ("cat_trf",OneHotEncoder(sparse_output=False),cat_features)])
        
            
        
        
        if model == "LinearRegression":
            final_pipe = Pipeline([("transformers",trf),("reg_model",LinearRegression())])
        elif model == "RandomForestRegressor":
            final_pipe = Pipeline([("transformers",trf),("rf_reg_model",RandomForestRegressor(random_state=42))])
        else:
            final_pipe = Pipeline([("transformers",trf),("reg_model",HistGradientBoostingRegressor(random_state=42))])

        final_pipe.fit(X_train,y_train)

        final_pipe.fit(X_train,y_train)

        #model = pickle.dump(final_pipe,open("regression_model","wb"))

        #y_hat = model.predict(X_train)

        return final_pipe, X_train,X_test,y_train,y_test
    if problem == "Classification":
        if model == "GradientBoosting":

            trf = ColumnTransformer([("num_trf",StandardScaler(),num_features),
                                    ("cat_trf",OneHotEncoder(),cat_features)])
            
            
            lbl_encd = LabelEncoder()

            lbl_encd.fit(y_train)
            y_train_trf = lbl_encd.transform(y_train)

            y_test_trf = lbl_encd.fit(y_test)
            
            final_pipe = Pipeline([("transformers",trf),("clf_model",GradientBoostingClassifier(random_state=42))])

            final_pipe.fit(X_train,y_train_trf)
            #file = open("model")
            #model = pickle.dump(final_pipe,("","wb"))

            return final_pipe, X_train,X_test,y_train_trf,y_test_trf
        elif model == "LogisticRegression":
            trf = ColumnTransformer([("num_trf",StandardScaler(),num_features),
                                    ("cat_trf",OneHotEncoder(),cat_features)])
            
            
            lbl_encd = LabelEncoder()

            lbl_encd.fit(y_train)
            y_train_trf = lbl_encd.transform(y_train)

            y_test_trf = lbl_encd.fit(y_test)
            
            final_pipe = Pipeline([("transformers",trf),("clf_model",LogisticRegression(random_state=42))])

            final_pipe.fit(X_train,y_train_trf)
            #file = open("model")
            #model = pickle.dump(final_pipe,("","wb"))

            return final_pipe, X_train,X_test,y_train_trf,y_test_trf


def predict(model=None,x=None):

    #m = pickle.load(open(model,"rb"))
    y_hat = model.predict(x)

    return y_hat

def evaluate(y_true,y_pred, problem="Regression"):

    if problem == "Regression":
        metric = r2_score(y_true,y_pred)
        return metric
    else:
        metric = classification_report(y_true,y_pred,output_dict=True)
        met_df = pd.DataFrame(metric).transpose()
        file = met_df.to_csv().encode('utf-8')

        return file
st.title("No Code Machine Learning Studio :six_pointed_star:")

st.image(image="https://www.silvertouchtech.co.uk/wp-content/uploads/2020/05/ai-banner.jpg")
st.subheader("Plug & Play Portal for Machine Learing")
    
prob_type = st.selectbox(label="Please select your ML problem type: ",options=("Regression","Classification"))

train_data = st.file_uploader(label="Please upload your training dataset",type=["csv"])

if prob_type == "Classification":

    model = st.selectbox(label="Plase Select your classification model: ", options=("GradientBoosting","LogisticRegression"))
else:
    model = st.selectbox(label="Plase Select your classification model: ", options=("LinearRegression","RandomForestRegressor","HistGradientBoostingRegressor"))


#def explain(model="LinearRegression",train_data=None,test_data=None):
#explainer = shap.LinearExplainer(model,train_data,feature_dependence=False)
#    shap_values = explainer.shap_values(test_data)

#    shap.summary_plot(shap_values,test_data,plot_type="violin",show=False)
#    mt.pyplot.gcf().axes[-1].set_box_aspect(10)


y = st.text_input("Please write your target column name:  ")
#num_f = st.text_input("Please write your numerical feature names(separted by ","): ").split(",")
#cat_f = st.text_input("Please write your categorical feature names(separted by ","): ").split(",")

if st.button("Train"):
    
    time.sleep(1)
    
    
    if prob_type=="Classification":
        with st.progress(10,"Discovering the dataset..."):
            time.sleep(0.5)
            st.progress(20, "Applying the preprocessing steps...")
            time.sleep(1)
            st.progress(25,"Training engine has started...")
            st.progress(50, "Training the model...")
            model_, X_train,X_test,y_train,y_test = train(data=train_data,problem=prob_type,model=model, label=y)
            time.sleep(2)
            st.progress(75, "Training complete...")
            st.progress(85, "Evaluating model performance...")
            st.progress(90, "Generating Classification report...")
            time.sleep(1)
            st.progress(100, "Complete! :100:")
        y_hat_train = predict(model_,X_train)
        y_hat_test = predict(model_,X_test)
        report = evaluate(y_train,y_hat_train,prob_type)

        st.download_button(label="Click here to download the report",data=report, mime="text/csv")
        time.sleep(2)
        st.write("Classification report of testing dataset: ")
        report_test = evaluate(y_train,y_hat_train,prob_type)
        st.download_button(key="test",label="Click here to download the report",data=report_test, mime="text/csv")
        st.success("Report generated successfully! :beers:")
        time.sleep(20)
    else:
        with st.progress(10,"Discovering the dataset..."):
            time.sleep(0.5)
            st.progress(20, "Applying the preprocessing steps...")
            time.sleep(1)
            st.progress(25,"Training engine has started...")
            st.progress(50, "Training the model...")
            model_, X_train,X_test,y_train,y_test = train(data=train_data,problem=prob_type,model=model, label=y)
            time.sleep(2)
            st.progress(75, "Training complete...")
            st.progress(85, "Evaluating model performance...")
            st.progress(90, "Generating Regression metrics...")
            time.sleep(1)
            st.progress(100, "Complete! :100:")
        y_hat_train = predict(model_,X_train)
        y_hat_test = predict(model_,X_test)
        st.write("r2 score on training set: ")
        st.write(evaluate(y_train,y_hat_train))
        st.write("r2 score on test set: ")
        time.sleep(0.5)

        st.write(evaluate(y_test,y_hat_test,prob_type)) 
        st.success("Metrics generated successfully! :beers:")