import gradio as gr
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier

#Loading the dataset
df = pd.read_csv('data/one_data.csv')

x_train, x_test, y_train, y_test = train_test_split(df.drop('CLASS', axis=1), df['CLASS'], test_size=0.2, random_state=42)

# Create a random forest classifier
rfc = RandomForestClassifier()

# Training the model using the training data
rfc.fit(x_train, y_train)

# Predicting the Loan Approval Status
#rfc_pred = rfc.predict(x_test)

def ml_model(a, b, c, d, e, f, g, h, i, j, k, l):
    test_data = [[a, b, c, d, e, f, g, h, i, j, k, l]]
    rfc_pred = rfc.predict(test_data)[0]
    dict = {
        0: "Acetic Acid",
        1: "Acetone",
        2: "Ammonia",
        3: "Ethanol",
        4: "Formic Acid",
        5: "Hydrochloric Acid",
        6: "Hydrogen Peroxide",
        7: "Phosphoric Acid",
        8: "Sodium Hypochlorite",
        9: "Sulphuric Acid",
        10: "Waste water"
    }
    class_name = f"Class : {dict[rfc_pred]}"
    return class_name, "Thank You"

demo = gr.Interface(
    fn=ml_model,
    inputs=[
        gr.Textbox(label="PLATINUM_78kHz_RESISTANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
        gr.Textbox(label="GOLD_78kHz_RESISTANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
        gr.Textbox(label="PLATINUM_200Hz_RESISTANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
        gr.Textbox(label="PLATINUM_200Hz_CAPACITANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
        gr.Textbox(label="GOLD_200Hz_RESISTANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
        gr.Textbox(label="GOLD_200Hz_CAPACITANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
        gr.Textbox(label="COPPER_200Hz_RESISTANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
        gr.Textbox(label="COPPER_200Hz_CAPACITANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
        gr.Textbox(label="SILVER_200Hz_RESISTANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
        gr.Textbox(label="SILVER_200Hz_CAPACITANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
        gr.Textbox(label="NICKEL_200Hz_RESISTANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
        gr.Textbox(label="NICKEL_200Hz_CAPACITANCE", placeholder="Enter data here..", elem_id="tbox", type='text'),
    ],
    outputs=["text", "text"],
    title="Aqua Alert",
    description="<strong><center> a ML Model which can predict contaminants present "
                "in the waste water</center> </strong>",
    theme=gr.themes.Soft(),
    css="""
        #tbox { color : black; width: 100 !important; }
        #tbox textarea {background-color: white; font-size : 15px; color : black;
         font-weight : bold; !important;}
    """,
    examples=[
        [2292.000, 13980.000, 1206.0000, -523.000, 4698.000, -3925.0000, 6757.0000, -3263.0000, 11269.000, -3596.000,
              14611.000, -1492.000],
        [3506, 16706, 22694, -4568, 14771, -2786, 15861, -1989, 15082, -2095, 17293, -133],
        [3230, 16109, 19895, -6970, 7621, -3032, 14481, -2957, 13919, -3001, 16518, -2134]
    ]
)

demo.launch(inbrowser=True)