import gradio as gr
import pandas as pd
from sklearn import datasets
import seaborn as sns
import matplotlib.pyplot as plt

def findCorrelation(dataset, target):
  
  print(dataset.name)
  print("\n")
  
  print(target)
  print(type(target))
  print(str(target))
  print("\n")
  
  df = pd.read_csv(dataset.name)
  print(df)
  print("\n")
  
  d = df.corr()[target].to_dict()
  d.pop(target)
  print(d)
  keys = sorted(d.items(), key=lambda x: x[0], reverse=True) 
    
  fig1 = plt.figure()
  hm = sns.heatmap(df.corr(), annot = True)
  hm.set(title = "Correlation matrix of dataset\n")
  
  fig2 = plt.figure()
  # use the function regplot to make a scatterplot
  sns.regplot(x=df[keys[0]], y=df[target])
  
  fig3 = plt.figure()
  # use the function regplot to make a scatterplot
  sns.regplot(x=df[keys[1]], y=df[target])

  fig4 = plt.figure()
  # use the function regplot to make a scatterplot
  sns.regplot(x=df[keys[2]], y=df[target])
  
  
  labels = {key: d[key] for key in keys[10]}
  
  return labels, fig1, fig2, fig3, fig4

demo = gr.Interface(fn=findCorrelation, inputs=[gr.File(), 'text'], outputs=[gr.Label(), gr.Plot(), gr.Plot(), gr.Plot(), gr.Plot()], title="Find correlation")
demo.launch(debug=True)