Update app.py

app.py

@@ -3,54 +3,37 @@ 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)
   
-  print(dataset.name)
-  print("\n")
-  
-  print(target)
-  print(type(target))
-  print(str(target))
-  print("\n")
+  non_numeric_cols = df.select_dtypes('object').columns.tolist()
   
-  df = pd.read_csv(dataset.name)
-  print(df)
-  print("\n")
+  for non_numeric_col in non_numeric_cols:
+    label_encoder = LabelEncoder()
+    df[non_numeric_col] = label_encoder.fit_transform(df[non_numeric_col])
   
   d = df.corr()[target].to_dict()
   d.pop(target)
-  print(d)
-  keys = sorted(d.items(), key=lambda x: x[0], reverse=True) 
-  
-  print(keys)
-  print(type(keys))
   
+  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")
-  
-  print("\n Fig 1")
     
   fig2 = plt.figure()
-  # use the function regplot to make a scatterplot
-  print(keys[0])
   sns.regplot(x=df[keys[0][0]], y=df[target])
-  print("\n Fig 2")
   
   fig3 = plt.figure()
-  # use the function regplot to make a scatterplot
   sns.regplot(x=df[keys[1][0]], y=df[target])
 
-  print("\n Fig 3")
-
   fig4 = plt.figure()
-  # use the function regplot to make a scatterplot
   sns.regplot(x=df[keys[2][0]], y=df[target])
-  
-  print("\n Fig 4")
    
   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 = gr.Interface(fn=findCorrelation, inputs=[gr.File(), 'text'], outputs=[gr.Label(num_top_classes = 6), gr.Plot(), gr.Plot(), gr.Plot(), gr.Plot()], title="Find correlation")
 demo.launch(debug=True)