app

app.py

@@ -1,6 +1,8 @@
 import pandas as pd
 import matplotlib.pyplot as plt
 import numpy as np
+from sklearn.preprocessing import LabelEncoder
+import seaborn as sns
 
 import gradio as gr
 
@@ -11,6 +13,18 @@ pd.options.display.max_rows = 300
 def outbreak(plot_type):
     df = pd.read_csv('emp_experience_data.csv')
     data_encoded = df.copy(deep=True)
+    categorical_column = ['Attrition', 'Gender', 'BusinessTravel', 'Education', 'EmployeeExperience', 'EmployeeFeedbackSentiments', 'Designation',
+                            'SalarySatisfaction', 'HealthBenefitsSatisfaction', 'UHGDiscountProgramUsage', 'HealthConscious', 'CareerPathSatisfaction', 'Region']
+    label_encoding = LabelEncoder()
+    for col in categorical_column:
+        data_encoded[col] = label_encoding.fit_transform(data_encoded[col])
+
+    if plot_type == "Find Data Correlation":
+        fig = plt.figure()
+        data_correlation = data_encoded.corr()
+        plt.rcParams["figure.figsize"] = [10,10]
+        sns.heatmap(data_correlation,xticklabels=data_correlation.columns,yticklabels=data_correlation.columns)
+        return fig
     if plot_type == "Age Attrition":
         fig = plt.figure()
         positive_attrition_df = data_encoded.loc[data_encoded['Attrition'] == "Yes"]
@@ -29,7 +43,7 @@ def outbreak(plot_type):
         return fig
 
 inputs = [
-        gr.Dropdown(["Age Attrition", "Distance Attrition"], label="Plot Type")
+        gr.Dropdown(["Find Data Correlation", "Age Attrition", "Distance Attrition"], label="Data Correlation and Visualization")
     ]
 
 outputs = gr.Plot()