import gradio as gr
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.svm import SVR
from sklearn.metrics import mean_squared_error

data = pd.read_csv("modeled_data.csv")

def sample_model(df, regressor, scale=None):
    X = df.drop("rate",axis=1)
    y = df["rate"]
    
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state=1)
    scaled_X_train, scaled_X_test = X_train, X_test
    if scale != None:
        scaler = scale
        scaled_X_train = pd.DataFrame(scaler.fit_transform(X_train), columns = X_train.columns)
        scaled_X_test = pd.DataFrame(scaler.transform(X_test),columns = X_test.columns)
    
    model = regressor
    model.fit(scaled_X_train, y_train)
    y_pred = model.predict(scaled_X_test)
    
    rmse = np.sqrt(mean_squared_error(y_test, y_pred))
    
    return model, scaled_X_train, scaled_X_test, y_train, y_test 


def user_interaction(comment, model):
    
    negative_score = analyzer.polarity_scores(comment)["neg"]
    neutral_score = analyzer.polarity_scores(comment)["neu"]
    positive_score = analyzer.polarity_scores(comment)["pos"]
    compound_score = analyzer.polarity_scores(comment)["compound"]
    rate_pred = model.predict([[negative_score, neutral_score, positive_score, compound_score]])
    
    print(f"\nYour Comment: {comment}\n")
    print("*"*10 + "Analysis of the Comment" + "*"*10)
    print("-"*10 + f"Negativity Score: {negative_score:.2f}" + "-"*10)
    print("-"*10 + f"Neutrality Score: {neutral_score:.2f}" + "-"*10)
    print("-"*10 + f"Positivity Score: {positive_score:.2f}" + "-"*10)
    print("-"*10 + f"Compound Score: {compound_score:.2f}" + "-"*10)
    print("*"*43)
    print("\nThe estimated rating this comment can give")
    print("*"*20 + str(round(rate_pred[0], 2)) + "*"*20)


def take_input(model):
    comment = input("Thanks for your interest and taking your time.\n"+
                    "Tell us about your personal experience enrolling in this course. Was it the right match for you?\n"+
                    "(Note: Comment should be written in English and be longer than 20 characters)\n")
    if (detect(comment) != "en") or (len(comment) < 20):
        print("Sorry, your comment does not meet the requirements.\n")
        take_input(model)
    else:
        user_interaction(comment, model)

cons_tuned_svr, _, _, _, _ = sample_model(data, SVR(C=3, kernel="rbf", tol=0.001))



iface = gr.Interface(fn=take_input(cons_tuned_svr), inputs="text", outputs="text")
iface.launch()