Update app.py

app.py

@@ -2,466 +2,641 @@ import numpy as np
 import pandas as pd
 import gradio as gr
 def greet(year,co2_emission,no2_emission,so2_emission,global_warming,methane_emission):
-    
-    #1996
+    import gradio as gr
+
+def greet(year,co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission):
   
-    #data collection
-    data1=pd.read_excel("FINAL_DATASET.xlsx")
-    df1 = data1.drop(['YEAR'], axis=1)
+  #1996
+  
+  #data collection
+  data1=pd.read_excel("FINAL_DATASET.xlsx")
+  df1 = data1.drop(['YEAR'], axis=1)
 
-    #data indexing
-    x=df1.iloc[:,1:].values
-    y=df1.iloc[:,0].values
-    np.reshape(y,(-1,1))
 
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+
+  #data indexing
+  x=df1.iloc[:,1:].values
+  y=df1.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
 
 
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred1=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
 
-    #Equation
-    total1="2.29209688*(x1)+(-17.24834114)*(x2)+(-34.46449984)*(x3)+441.88734541(x4)+(-10.5704468)*(x5)+3032.3276611889232"
-     
-    #1997
-    
-    #data collection
-    data2=pd.read_excel("ans1.xlsx")
-    df2 = data2.drop(['YEAR '], axis=1)
-
-    #data indexing
-    x=df2.iloc[:,1:].values
-    y=df2.iloc[:,0].values
-    np.reshape(y,(-1,1))
-
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred1=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total1="2.29209688*(x1)+(-17.24834114)*(x2)+(-34.46449984)*(x3)+441.88734541(x4)+(-10.5704468)*(x5)+3032.3276611889232"
+  
+
+  #1997
+
+  #data collection
+  data2=pd.read_excel("ans1.xlsx")
+  df2 = data2.drop(['YEAR '], axis=1)
+
+
+
+  #data indexing
+  x=df2.iloc[:,1:].values
+  y=df2.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
 
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred2=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
 
-    #Equation
-    total2="1.87191609*(x1)+19.64115875*(x2)+91.64048224*(x3)+188.38350818*(x4)+23.55498894*(x5)-10954.252919457198"
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred2=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
   
-    #1998
 
-    #data collection
-    data3=pd.read_excel("ans2.xlsx")
-    df3 = data3.drop([' YEAR '], axis=1)
-    
-    #data indexing
-    x=df3.iloc[:,1:].values
-    y=df3.iloc[:,0].values
-    np.reshape(y,(-1,1))
-
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+  #Equation
+  total2="1.87191609*(x1)+19.64115875*(x2)+91.64048224*(x3)+188.38350818*(x4)+23.55498894*(x5)-10954.252919457198"
+  
+
+
+   #1998
+
+  #data collection
+  data3=pd.read_excel("ans2.xlsx")
+  df3 = data3.drop([' YEAR '], axis=1)
+
+
+
+  #data indexing
+  x=df3.iloc[:,1:].values
+  y=df3.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
 
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred3=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
-    
-    #Equation
-    total3="-16.16933055*(x1)+222.22199705*(x2)+137.12332335*(x3)+325.31073157*(x4)+(-123.63496668)*(x5)+56972.685015326366"
-    
-    #1999
-    
-    #data collection
-    
-    data4=pd.read_excel("/content/ans3.xlsx")
-    df4 = data4.drop([' YEAR '], axis=1)
-    
-    #data indexing
-    x=df4.iloc[:,1:].values
-    y=df4.iloc[:,0].values
-    np.reshape(y,(-1,1))
-    
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred3=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total3="-16.16933055*(x1)+222.22199705*(x2)+137.12332335*(x3)+325.31073157*(x4)+(-123.63496668)*(x5)+56972.685015326366"
+  
+
+
+  #1999
+
+  #data collection
+  data4=pd.read_excel("ans3.xlsx")
+  df4 = data4.drop([' YEAR '], axis=1)
+
+
+
+  #data indexing
+  x=df4.iloc[:,1:].values
+  y=df4.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
-    
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred4=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
-    
-    
-    #Equation
-    total4="24.45036879*(x1)+(-30.15985323)*(x2)+40.89603753*(x3)+102.95011027*(x4)+(-26.35323684)*(x5)+7934.309705068432"
-    
-    #2000
-    
-    #data collection
-    
-    data5=pd.read_excel("/content/ans4.xlsx")
-    df5 = data5.drop([' YEAR '], axis=1)
-    
-    #data indexing
-    
-    x=df5.iloc[:,1:].values
-    y=df5.iloc[:,0].values
-    np.reshape(y,(-1,1))
-    
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+
+
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred4=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total4="24.45036879*(x1)+(-30.15985323)*(x2)+40.89603753*(x3)+102.95011027*(x4)+(-26.35323684)*(x5)+7934.309705068432"
+  
+
+
+  #2000
+
+  #data collection
+  data5=pd.read_excel("ans4.xlsx")
+  df5 = data5.drop([' YEAR '], axis=1)
+
+
+
+  #data indexing
+  x=df5.iloc[:,1:].values
+  y=df5.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
-    
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred5=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
-    
-    #Equation
-    total5="9.64446417*(x1)+1536.50170104*(x2)+(-43.51829088)*(x3)+(-209.86341104)*(x4)+(-56.82344007)*(x5)+21672.006533155447"
-    
+
+
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred5=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total5="9.64446417*(x1)+1536.50170104*(x2)+(-43.51829088)*(x3)+(-209.86341104)*(x4)+(-56.82344007)*(x5)+21672.006533155447"
+  
+
+
     #2001
-    
-    #data collection
-    
-    data6=pd.read_excel("/content/ans5.xlsx")
-    df6 = data6.drop([' YEAR '], axis=1)
-    
-    #data indexing
-    
-    x=df6.iloc[:,1:].values
-    y=df6.iloc[:,0].values
-    np.reshape(y,(-1,1))
-    
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+
+  #data collection
+  data6=pd.read_excel("ans5.xlsx")
+  df6 = data6.drop([' YEAR '], axis=1)
+
+
+
+  #data indexing
+  x=df6.iloc[:,1:].values
+  y=df6.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
-    
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred6=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
-    
-    #Equation
-    total6="(-17.95980305)*(x1)+397.29027184*(x2)+332.85116421*(x3)+176.63505073*(x4)+(-100.69005777)*(x5)+47882.75497380103"
+
+
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred6=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total6="(-17.95980305)*(x1)+397.29027184*(x2)+332.85116421*(x3)+176.63505073*(x4)+(-100.69005777)*(x5)+47882.75497380103"
  
 
     #2002
 
-    #data collection
-    
-    data7=pd.read_excel("/content/ans6.xlsx")
-    df7 = data7.drop([' YEAR '], axis=1)
+  #data collection
+  data7=pd.read_excel("ans6.xlsx")
+  df7 = data7.drop([' YEAR '], axis=1)
 
-    #data indexing
-    x=df7.iloc[:,1:].values
-    y=df7.iloc[:,0].values
-    np.reshape(y,(-1,1))
 
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+
+  #data indexing
+  x=df7.iloc[:,1:].values
+  y=df7.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
-    
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred7=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
 
 
-    #Equation
-    total7="4.08573322*(x1)+531.87792204*(x2)+(-17.3614085 )*(x3)+(-11.17919737)*(x4)+(-53.48796076)*(x5)+22953.88111229325"
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred7=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total7="4.08573322*(x1)+531.87792204*(x2)+(-17.3614085 )*(x3)+(-11.17919737)*(x4)+(-53.48796076)*(x5)+22953.88111229325"
   
 
     #2003
 
-    #data collection
-    data8=pd.read_excel("/content/ans7.xlsx")
-    df8 = data8.drop([' YEAR '], axis=1)
-    
-    #data indexing
-    x=df8.iloc[:,1:].values
-    y=df8.iloc[:,0].values
-    np.reshape(y,(-1,1))
-
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+  #data collection
+  data8=pd.read_excel("ans7.xlsx")
+  df8 = data8.drop([' YEAR '], axis=1)
+
+
+
+  #data indexing
+  x=df8.iloc[:,1:].values
+  y=df8.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
-    
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred8=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
 
 
-    #Equation
-    total8="31.82512443*(x1)+(-521.96868383 )*(x2)+(-43.51829088)*(x3)+ 205.27514768 *(x4)+(-97.91577198)*(x5)+37973.451433772294"
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
   
 
+  y_pred8=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total8="31.82512443*(x1)+(-521.96868383 )*(x2)+(-43.51829088)*(x3)+ 205.27514768 *(x4)+(-97.91577198)*(x5)+37973.451433772294"
+  
+
+
     #2004
 
-    #data collection
-    data9=pd.read_excel("/content/ans8.xlsx")
-    df9 = data9.drop([' YEAR '], axis=1)
+  #data collection
+  data9=pd.read_excel("ans8.xlsx")
+  df9 = data9.drop([' YEAR '], axis=1)
 
 
-    #data indexing
-    x=df9.iloc[:,1:].values
-    y=df9.iloc[:,0].values
-    np.reshape(y,(-1,1))
-    
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+
+  #data indexing
+  x=df9.iloc[:,1:].values
+  y=df9.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
 
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred9=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
 
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
 
-    #Equation
-    total9="9.64446417*(x1)+1536.50170104*(x2)+(-43.51829088)*(x3)+(-209.86341104)*(x4)+(-56.82344007)*(x5)+21672.006533155447"
+  reg = LinearRegression().fit(X_train, y_train)
   
 
+  y_pred9=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total9="9.64446417*(x1)+1536.50170104*(x2)+(-43.51829088)*(x3)+(-209.86341104)*(x4)+(-56.82344007)*(x5)+21672.006533155447"
+  
+
+
     #2005
-    
-    #data collection
-    data10=pd.read_excel("/content/ans9.xlsx")
-    df10 = data10.drop([' YEAR '], axis=1)
-    
-    #data indexing
-    x=df10.iloc[:,1:].values
-    y=df10.iloc[:,0].values
-    np.reshape(y,(-1,1))
-    
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+
+  #data collection
+  data10=pd.read_excel("ans9.xlsx")
+  df10 = data10.drop([' YEAR '], axis=1)
+
+
+
+  #data indexing
+  x=df10.iloc[:,1:].values
+  y=df10.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
-    
-    
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred10=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
 
 
-    #Equation
-    total10="(-46.41395388)*(x1)+27.19076539*(x2)+(442.44336049)*(x3)+(-205.61881527)*(x4)+120.39426307*(x5)-46289.48823133327"
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred10=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total10="(-46.41395388)*(x1)+27.19076539*(x2)+(442.44336049)*(x3)+(-205.61881527)*(x4)+120.39426307*(x5)-46289.48823133327"
   
 
+
     #2006
 
-    #data collection
-    data11=pd.read_excel("/content/ans10.xlsx")
-    df11 = data11.drop([' YEAR '], axis=1)
-    
-    #data indexing
-    x=df11.iloc[:,1:].values
-    y=df11.iloc[:,0].values
-    np.reshape(y,(-1,1))
-    
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+  #data collection
+  data11=pd.read_excel("ans10.xlsx")
+  df11 = data11.drop([' YEAR '], axis=1)
+
+
+
+  #data indexing
+  x=df11.iloc[:,1:].values
+  y=df11.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
-    
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred11=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
 
 
-    #Equation
-    total11="(-15.45736104)*(x1)+23.92398419*(x2)+334.30252317*(x3)+151.55678804*(x4)+(-66.42769537)*(x5)+29294.014037250927"
-    
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred11=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total11="(-15.45736104)*(x1)+23.92398419*(x2)+334.30252317*(x3)+151.55678804*(x4)+(-66.42769537)*(x5)+29294.014037250927"
+  
+
+
+
     #2007
 
-    #data collection
-    data12=pd.read_excel("/content/ans11.xlsx")
-    df12 = data12.drop([' YEAR '], axis=1)
+  #data collection
+  data12=pd.read_excel("ans11.xlsx")
+  df12 = data12.drop([' YEAR '], axis=1)
+
 
-    #data indexing
-    x=df12.iloc[:,1:].values
-    y=df12.iloc[:,0].values
-    np.reshape(y,(-1,1))
-    
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+
+  #data indexing
+  x=df12.iloc[:,1:].values
+  y=df12.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
-    
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred12=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
 
 
-    #Equation
-    total12="33.41323832*(x1)+(-36.18735569)*(x2)+768.11444325*(x3)+(-182.42626044 )*(x4)+(14.70116631)*(x5)-6967.764713347897"
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred12=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total12="33.41323832*(x1)+(-36.18735569)*(x2)+768.11444325*(x3)+(-182.42626044 )*(x4)+(14.70116631)*(x5)-6967.764713347897"
   
+
+
     #2008
 
-    #data collection
-    data13=pd.read_excel("/content/ans12.xlsx")
-    df13 = data13.drop([' YEAR '], axis=1)
+  #data collection
+  data13=pd.read_excel("ans12.xlsx")
+  df13 = data13.drop([' YEAR '], axis=1)
+
 
-    #data indexing
-    x=df13.iloc[:,1:].values
-    y=df13.iloc[:,0].values
-    np.reshape(y,(-1,1))
 
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+  #data indexing
+  x=df13.iloc[:,1:].values
+  y=df13.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
-    
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred13=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
 
-    #Equation
-    total13="180.34683409 *(x1)+49.48628012*(x2)+152.71729516*(x3)+( -174.89679207)*(x4)+(-144.40854904)*(x5)+30420.505686819404"
+
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
   
 
-    #2009
+  y_pred13=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
 
-    #data collection
-    data14=pd.read_excel("/content/ans13.xlsx")
-    df14 = data14.drop([' YEAR '], axis=1)
+  #Equation
+  total13="180.34683409 *(x1)+49.48628012*(x2)+152.71729516*(x3)+( -174.89679207)*(x4)+(-144.40854904)*(x5)+30420.505686819404"
+  
 
-    #data indexing
-    x=df14.iloc[:,1:].values
-    y=df14.iloc[:,0].values
-    np.reshape(y,(-1,1))
     
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+
+
+    #2009
+
+  #data collection
+  data14=pd.read_excel("ans13.xlsx")
+  df14 = data14.drop([' YEAR '], axis=1)
+
+
+
+  #data indexing
+  x=df14.iloc[:,1:].values
+  y=df14.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
-    
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred14=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
 
 
-    #Equation
-    total14="17.11355138 *(x1)+37.59837451*(x2)+156.43469383*(x3)+(-104.8362236)*(x4)+81.10973597*(x5)-38919.678559060834"
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred14=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
   
 
+  #Equation
+  total14="17.11355138 *(x1)+37.59837451*(x2)+156.43469383*(x3)+(-104.8362236)*(x4)+81.10973597*(x5)-38919.678559060834"
+  
+
+
+
     #2010
-    
-    #data collection
-    data15=pd.read_excel("/content/ans14.xlsx")
-    df15 = data15.drop([' YEAR '], axis=1)
-
-    #data indexing
-    x=df15.iloc[:,1:].values
-    y=df15.iloc[:,0].values
-    np.reshape(y,(-1,1))
-    
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+
+  #data collection
+  data15=pd.read_excel("ans14.xlsx")
+  df15 = data15.drop([' YEAR '], axis=1)
+
+
+
+  #data indexing
+  x=df15.iloc[:,1:].values
+  y=df15.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
-    
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred15=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
 
-    #Equation
-    total15="39.06418699 *(x1)+148.53455807*(x2)+14.69213499 *(x3)+107.43795246*(x4)+(-207.77185028)*(x5)+82358.63651384937"
+
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred15=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total15="39.06418699 *(x1)+148.53455807*(x2)+14.69213499 *(x3)+107.43795246*(x4)+(-207.77185028)*(x5)+82358.63651384937"
   
 
 
 
     #2011
 
-    #data collection
-    data16=pd.read_excel("/content/ans15.xlsx")
-    df16 = data16.drop([' YEAR '], axis=1)
+  #data collection
+  data16=pd.read_excel("ans15.xlsx")
+  df16 = data16.drop([' YEAR '], axis=1)
+
 
-    #data indexing
-    x=df16.iloc[:,1:].values
-    y=df16.iloc[:,0].values
-    np.reshape(y,(-1,1))
 
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+  #data indexing
+  x=df16.iloc[:,1:].values
+  y=df16.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
 
 
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred16=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
 
-    #Equation
-    total16="36.2551509 *(x1)+-21.16118114*(x2)+372.06856269*(x3)+(-59.04384028)*(x4)+(-49.61395171)*(x5)+18259.681897588325"
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred16=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+
+  
+
+  #Equation
+  total16="36.2551509 *(x1)+-21.16118114*(x2)+372.06856269*(x3)+(-59.04384028)*(x4)+(-49.61395171)*(x5)+18259.681897588325"
   
 
 
 
     #2012
-    
-    #data collection
-    data17=pd.read_excel("/content/ans16.xlsx")
-    df17 = data17.drop([' YEAR '], axis=1)
-    
-    #data indexing
-    x=df17.iloc[:,1:].values
-    y=df17.iloc[:,0].values
-    np.reshape(y,(-1,1))
-
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+
+  #data collection
+  data17=pd.read_excel("ans16.xlsx")
+  df17 = data17.drop([' YEAR '], axis=1)
+
+
+
+  #data indexing
+  x=df17.iloc[:,1:].values
+  y=df17.iloc[:,0].values
+  np.reshape(y,(-1,1))
+
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
 
 
-    #traing the dataset
-    from sklearn.linear_model import LinearRegression
-    reg = LinearRegression().fit(X_train, y_train)
-    y_pred17=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+  #traing the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  
+
+  y_pred17=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
 
 
-    #Equation
-    total17="76.15862868 *(x1)+24.66304806*(x2)+(-31.1753211)*(x3)+(-281.13550722 )*(x4)+48.76763872*(x5)-27641.15357666507"
+  
+
+  #Equation
+  total17="76.15862868 *(x1)+24.66304806*(x2)+(-31.1753211)*(x3)+(-281.13550722 )*(x4)+48.76763872*(x5)-27641.15357666507"
   
 
 
     #2013
 
-    #data collection
-    data18=pd.read_excel("/content/ans17.xlsx")
-    df18 = data18.drop([' YEAR '], axis=1)
+  #data collection
+  data18=pd.read_excel("ans17.xlsx")
+  df18 = data18.drop([' YEAR '], axis=1)
 
 
 
-    #data indexing
-    x=df18.iloc[:,1:].values
-    y=df18.iloc[:,0].values
-    np.reshape(y,(-1,1))
+  #data indexing
+  x=df18.iloc[:,1:].values
+  y=df18.iloc[:,0].values
+  np.reshape(y,(-1,1))
 
-    #split the dataset
-    from sklearn.model_selection import train_test_split
-    X_train, X_test, y_train, y_test = train_test_split(
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
       x, y, test_size=0.33, random_state=42)
 
 
@@ -487,7 +662,7 @@ def greet(year,co2_emission,no2_emission,so2_emission,global_warming,methane_emi
     #2014
 
   #data collection
-  data19=pd.read_excel("/content/ans18.xlsx")
+  data19=pd.read_excel("ans18.xlsx")
   df19 = data19.drop([' YEAR '], axis=1)
 
 
@@ -525,7 +700,7 @@ def greet(year,co2_emission,no2_emission,so2_emission,global_warming,methane_emi
     #2015
 
   #data collection
-  data20=pd.read_excel("/content/ans19.xlsx")
+  data20=pd.read_excel("ans19.xlsx")
   df20 = data20.drop([' YEAR '], axis=1)
 
 
@@ -565,7 +740,7 @@ def greet(year,co2_emission,no2_emission,so2_emission,global_warming,methane_emi
     #2016
 
   #data collection
-  data21=pd.read_excel("/content/ans20.xlsx")
+  data21=pd.read_excel("ans20.xlsx")
   df21 = data21.drop([' YEAR '], axis=1)
 
 
@@ -603,7 +778,7 @@ def greet(year,co2_emission,no2_emission,so2_emission,global_warming,methane_emi
     #2017
 
   #data collection
-  data22=pd.read_excel("/content/ans21.xlsx")
+  data22=pd.read_excel("ans21.xlsx")
   df22 = data22.drop([' YEAR '], axis=1)
 
 
@@ -641,7 +816,7 @@ def greet(year,co2_emission,no2_emission,so2_emission,global_warming,methane_emi
     #2018
 
   #data collection
-  data23=pd.read_excel("/content/ans22.xlsx")
+  data23=pd.read_excel("ans22.xlsx")
   df23 = data23.drop([' YEAR '], axis=1)
 
 
@@ -678,7 +853,7 @@ def greet(year,co2_emission,no2_emission,so2_emission,global_warming,methane_emi
     #2019
 
   #data collection
-  data24=pd.read_excel("/content/ans23.xlsx")
+  data24=pd.read_excel("ans23.xlsx")
   df24 = data24.drop([' YEAR '], axis=1)
 
 
@@ -716,7 +891,7 @@ def greet(year,co2_emission,no2_emission,so2_emission,global_warming,methane_emi
     #2020
 
   #data collection
-  data25=pd.read_excel("/content/ans24.xlsx")
+  data25=pd.read_excel("ans24.xlsx")
   df25 = data25.drop([' YEAR '], axis=1)
 
 
@@ -754,7 +929,7 @@ def greet(year,co2_emission,no2_emission,so2_emission,global_warming,methane_emi
     #2021
 
   #data collection
-  data26=pd.read_excel("/content/ans25.xlsx")
+  data26=pd.read_excel("ans25.xlsx")
   df26 = data26.drop([' YEAR '], axis=1)
 
 
@@ -792,7 +967,7 @@ def greet(year,co2_emission,no2_emission,so2_emission,global_warming,methane_emi
     #2022
 
   #data collection
-  data27=pd.read_excel("/content/ans26.xlsx")
+  data27=pd.read_excel("ans26.xlsx")
   df27 = data27.drop([' YEAR '], axis=1)
 
 
@@ -820,20 +995,120 @@ def greet(year,co2_emission,no2_emission,so2_emission,global_warming,methane_emi
   #Equation
   total27="15.98972327*(x1)+5568.67299429*(x2)+79.28661735*(x3)+16.79333316*(x4)+(-87.10169494)*(x5)+40155.32700035415"
   
-    
-    data=pd.read_excel("bara shigiri - Copy.xlsx")
-    x=data.iloc[:,1:].values
-    y=data.iloc[:,0].values
-    np.reshape(y,(-1,1))
-    from sklearn.model_selection import train_test_split
-    from sklearn.linear_model import LinearRegression
-    X_train, X_test, y_train, y_test = train_test_split(x,y,test_size=0.33,random_state=42)
-    reg=LinearRegression().fit(X_train,y_train)
-    eqn="-1.50608097*(x1) +(10.05272793)*(x2) +(-10.52662062)*(x3) +336.60218769*(x4) +(-23.82408478)*(x5) +12129.976853563849"
-    y_pred=reg.predict([[co2_emission,no2_emission,so2_emission,global_warming,methane_emission]])
-
-    if(year>=2023):
-        return eqn,y_pred
+
+  #above 2023
+  data28=pd.read_excel("bara shigiri - Copy.xlsx")
+
+  #data indexing 
+  x=data28.iloc[:,1:].values
+  y=data28.iloc[:,0].values
+  np.reshape(y,(-1,1)) 
+  
+  #split the dataset
+  from sklearn.model_selection import train_test_split
+  X_train, X_test, y_train, y_test = train_test_split(
+      x, y, test_size=0.33, random_state=42)
+  
+  #training the dataset
+  from sklearn.linear_model import LinearRegression
+
+  reg = LinearRegression().fit(X_train, y_train)
+  y_pred28=reg.predict([[co2_emission,No2_emission,so2_emission,Global_Warming,Methane_emission]])
+
+
+  
+  #Equation
+  total28="-1.50608097*(x1)+10.05272793*(x2)+(-10.52662062)*(x3)+336.60218769*(x4)+(-23.82408478)*(x5)+12129.976853563849"
+
+
+  #app section
+  if(year==1996):
+    return total1,y_pred1
+
+  elif(year==1997):
+    return total2,y_pred2
+
+  elif(year==1998):
+    return total3,y_pred3
+
+  elif(year==1999):
+    return total4,y_pred4
+
+  elif(year==2000):
+    return total5,y_pred5
+
+  elif(year==2001):
+    return total6,y_pred6
+
+  elif(year==2002):
+    return total7,y_pred7
+  
+  elif(year==2003):
+    return total8,y_pred8
+
+  elif(year==2004):
+    return total9,y_pred9
+
+  elif(year==2005):
+    return total10,y_pred10
+
+  elif(year==2006):
+    return total11,y_pred11
+
+  elif(year==2007):
+    return total12,y_pred12
+
+  elif(year==2008):
+    return total13,y_pred13
+
+  elif(year==2009):
+    return total14,y_pred14
+
+  elif(year==2010):
+    return total15,y_pred15
+
+  elif(year==2011):
+    return total16,y_pred16
+
+  elif(year==2012):
+    return total17,y_pred17
+
+  elif(year==2013):
+    return total18,y_pred18
+
+  elif(year==2014):
+    return total19,y_pred19
+
+  elif(year==2015):
+    return total20,y_pred20
+
+  elif(year==2016):
+    return total21,y_pred21
+
+  elif(year==2017):
+    return total22,y_pred22
+
+  elif(year==2018):
+    return total23,y_pred23
+
+  elif(year==2019):
+    return total24,y_pred24
+
+  elif(year==2020):
+    return total25,y_pred25
+
+  elif(year==2021):
+    return total26,y_pred26
+
+  elif(year==2022):
+    return total27,y_pred27
+      
+  elif(year>=2023):
+    return total28,y_pred28
+
+  else:
+      return "no",0
+
 
 demo = gr.Interface(
     fn=greet,