Updated Code

app.py

@@ -5,29 +5,19 @@ 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()
-
-
-
+df.nunique() #Checking the number of unique values for primary keys or constants
+df.isna().sum()#Missing values 
 h_mean=df["height"].mean()
 w_mean=df["weight"].mean()
 age_mean=df["age"].mean()
 g_mode=df["gender"].mode()[0]
+r_mode=df["reported_sleep_hours"].mode()[0]
+n_mode=df["nap_duration"].mode()[0]
 p1=df["phq1"].mode()[0]
 p2=df["phq2"].mode()[0]
 p3=df["phq3"].mode()[0]
@@ -37,12 +27,7 @@ p6=df["phq6"].mode()[0]
 p7=df["phq7"].mode()[0]
 p8=df["phq8"].mode()[0]
 p9=df["phq9"].mode()[0]
-
-
-p5
-
-
-
+r_mode
 df["height"].fillna(h_mean,inplace=True)
 df["weight"].fillna(w_mean,inplace=True)
 df["age"].fillna(age_mean,inplace=True)
@@ -56,11 +41,26 @@ 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["reported_sleep_hours"].fillna(r_mode,inplace=True)
+df["nap_duration"].fillna(n_mode,inplace=True)
 
 df.isna().sum()
 
-df["reported_sleep_hours"][0]
-
+import datetime
+new=[]
+for i in range(len(df["reported_sleep_hours"])):
+    con=datetime.datetime.strptime(str(df["reported_sleep_hours"][i]),"%H:%M")
+    t=float(con.minute/60)
+    tot=float(con.hour)+t
+    new.append(tot)
+df.insert(44,"reported_sleep_in_hours",new)
+new=[]
+for i in range(len(df["nap_duration"])):
+    con=datetime.datetime.strptime(str(df["nap_duration"][i]),"%H:%M")
+    t=float(con.minute/60)
+    tot=float(con.hour)+t
+    new.append(tot)
+df.insert(45,"nap_duration_hours",new)
 
 from sklearn import preprocessing  
 le= preprocessing.LabelEncoder()
@@ -68,36 +68,30 @@ 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"]
+# In[22]:
 
 
+X=df[["age","gender","height","weight","phq1","phq2","phq3","phq4","phq5","phq6","phq7","phq8","phq9","reported_sleep_in_hours","nap_duration_hours"]]
+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,"%")
 
+y_pred = model.predict(X_test)
+print('Coefficients: \n', model.coef_)
+print("Mean squared error: %.2f" % np.mean((model.predict(X_test) - y_test) ** 2))
 
-df["gad_total"].max()
-
-
-
-df["gad_total"]
-
-
-def greet(name):
-    return "Hello " + name + "!!"
+def greet(input):
+    temp= input.split(",")
+    y = model.predict([[temp[0],temp[1],temp[2],temp[3],temp[4],temp[5],temp[6],temp[7],temp[8],temp[9],temp[10],temp[11],temp[12],temp[13],temp[14],temp[15]]])
+    y = str(y)
+    return y
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+iface = gr.Interface(fn=greet, inputs="text", outputs="text").launch(share=True)