File size: 1,066 Bytes
fac37fe
 
 
 
 
 
d4e49b0
43ca9c2
e42834f
43ca9c2
e42834f
6448874
d1797c8
d4e49b0
 
d1797c8
6448874
 
fac37fe
d4e49b0
6448874
 
fac37fe
d1797c8
d4e49b0
 
 
d1797c8
d4e49b0
 
 
d1797c8
6448874
d4e49b0
fac37fe
d4e49b0
e7c616e
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
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)
  
  df = pd.read_csv(dataset.name)
  
  d = df.corr()[target].to_dict()
  labels = sorted(d.items(), key=lambda x: x[1], reverse=True)
  
  labels.pop(target)
  
  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=labels.keys()[0], y=df[target])
  
  fig3 = plt.figure()
  # use the function regplot to make a scatterplot
  sns.regplot(x=labels.keys()[1], y=df[target])

  fig4 = plt.figure()
  # use the function regplot to make a scatterplot
  sns.regplot(x=labels.keys()[2], y=df[target])
  
  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)