app.py

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

def findCorrelation(dataset, target):
 
 df = pd.read_csv(dataset.name)
 
 non_numeric_cols = df.select_dtypes('object').columns.tolist()
 
 if target in non_numeric_cols:
 label_encoder = LabelEncoder()
 df[non_numeric_col] = label_encoder.fit_transform(df[target])
 
 d = df.corr()[target].to_dict()
 d.pop(target)
 
 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()
 sns.regplot(x=df[keys[0][0]], y=df[target])
 
 fig3 = plt.figure()
 sns.regplot(x=df[keys[1][0]], y=df[target])

 fig4 = plt.figure()
 sns.regplot(x=df[keys[2][0]], y=df[target])
 
 return d, fig1, fig2, fig3, fig4

demo = gr.Interface(fn=findCorrelation, inputs=[gr.File(), 'text'], outputs=[gr.Label(num_top_classes = 10), gr.Plot(), gr.Plot(), gr.Plot(), gr.Plot()], title="Find correlation")
demo.launch(debug=True)