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")
    
  try:
    fig2 = plt.figure()
    sns.regplot(x=df[keys[0][0]], y=df[target])
  except:
    fig2 = plt.figure()
  
  try:
    fig3 = plt.figure()
    sns.regplot(x=df[keys[1][0]], y=df[target])
  except:
    fig3 = plt.figure()

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

css = """
footer {display:none !important}
.output-markdown{display:none !important}

div[data-testid="label"] {height: 18rem !important; overflow-x : hidden !important; overflow-y: scroll !important;}
.max-h-\[30rem\] {max-height: 18rem !important;}

.gr-button-lg {
    z-index: 14;
    width: 113px;
    height: 30px;
    left: 0px;
    top: 0px;
    padding: 0px;
    cursor: pointer !important; 
    background: none rgb(17, 20, 45) !important;
    border: none !important;
    text-align: center !important;
    font-size: 14px !important;
    font-weight: 500 !important;
    color: rgb(255, 255, 255) !important;
    line-height: 1 !important;
    border-radius: 6px !important;
    transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
    box-shadow: none !important;
}
.gr-button-lg:hover{
    z-index: 14;
    width: 113px;
    height: 30px;
    left: 0px;
    top: 0px;
    padding: 0px;
    cursor: pointer !important; 
    background: none rgb(37, 56, 133) !important;
    border: none !important;
    text-align: center !important;
    font-size: 14px !important;
    font-weight: 500 !important;
    color: rgb(255, 255, 255) !important;
    line-height: 1 !important;
    border-radius: 6px !important;
    transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
    box-shadow: rgb(0 0 0 / 23%) 0px 1px 7px 0px !important;
}


.hover\:bg-orange-50:hover {
    --tw-bg-opacity: 1 !important;
    background-color: rgb(229,225,255) !important;
}

.to-orange-200 {
    --tw-gradient-to: rgb(37 56 133 / 37%) !important;
}
.from-orange-400 {
    --tw-gradient-from: rgb(17, 20, 45) !important;
    --tw-gradient-to: rgb(255 150 51 / 0);
    --tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to) !important;
}
.group-hover\:from-orange-500{
    --tw-gradient-from:rgb(17, 20, 45) !important; 
    --tw-gradient-to: rgb(37 56 133 / 37%);
    --tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to) !important;
}
.group:hover .group-hover\:text-orange-500{
    --tw-text-opacity: 1 !important;
    color:rgb(37 56 133 / var(--tw-text-opacity)) !important;
}

"""

with gr.Blocks(title="Find Correlation | Data Science Dojo", css = css) as demo:
    with gr.Row():
      with gr.Column():
        file = gr.File()
      with gr.Column():
        inp = gr.Textbox(placeholder="Enter the target feature name", label="Target Variable")
    btn = gr.Button("Find correlation")
    gr.Markdown(
            """
            ## Correlation with other numeric features
            """)
    with gr.Row():
       labels = gr.Label(num_top_classes = 10)
    gr.Markdown(
            """
            ## HeatMap
            """)
    with gr.Row():
       fig1 = gr.Plot()
    gr.Markdown(
            """
            ## Plot of top 3 correlated features
            """)
    with gr.Row():
       with gr.Column():
         fig2 = gr.Plot()
       with gr.Column():
         fig3 = gr.Plot()
    with gr.Row():
       fig4 = gr.Plot()
    with gr.Row():
      gr.Examples(
                examples = [["boston.csv", "MEDV"]], fn=findCorrelation, inputs=[file, inp], outputs=[labels, fig1, fig2, fig3, fig4], cache_examples=True)
    btn.click( fn=findCorrelation, inputs=[file, inp], outputs=[labels, fig1, fig2, fig3, fig4])

demo.launch()