import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
import gradio as gr

df=pd.read_csv("mexican_medical_students_mental_health_data.csv")

df.head()
df.info

target=df.iloc[:,19:27].sum(axis=1)

df.insert(43,"gad_total",target)

df.head()



df.nunique()


df.isna().sum()



h_mean=df["height"].mean()
w_mean=df["weight"].mean()
age_mean=df["age"].mean()
g_mode=df["gender"].mode()[0]
p1=df["phq1"].mode()[0]
p2=df["phq2"].mode()[0]
p3=df["phq3"].mode()[0]
p4=df["phq4"].mode()[0]
p5=df["phq5"].mode()[0]
p6=df["phq6"].mode()[0]
p7=df["phq7"].mode()[0]
p8=df["phq8"].mode()[0]
p9=df["phq9"].mode()[0]


p5



df["height"].fillna(h_mean,inplace=True)
df["weight"].fillna(w_mean,inplace=True)
df["age"].fillna(age_mean,inplace=True)
df["gender"].fillna(g_mode,inplace=True)
df["phq1"].fillna(p1,inplace=True)
df["phq2"].fillna(p2,inplace=True)
df["phq3"].fillna(p3,inplace=True)
df["phq4"].fillna(p4,inplace=True)
df["phq5"].fillna(p5,inplace=True)
df["phq6"].fillna(p6,inplace=True)
df["phq7"].fillna(p7,inplace=True)
df["phq8"].fillna(p8,inplace=True)
df["phq9"].fillna(p9,inplace=True)

df.isna().sum()

df["reported_sleep_hours"][0]


from sklearn import preprocessing  
le= preprocessing.LabelEncoder()
df["gender"]=le.fit_transform(df["gender"])
df.head()


X=df[["age","gender","height","weight","phq1","phq2","phq3","phq4","phq5","phq6","phq7","phq8","phq9"]]
y=df["gad_total"]



X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=21)


model=LinearRegression()



model.fit(X_train,y_train)
print("Training complete.")



r2_score=model.score(X_test,y_test)
print(r2_score*100,"%")


df["gad_total"].max()



df["gad_total"]


def greet(name):
    return "Hello " + name + "!!"

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