This refactoring separates different functionalities into functions, uses more descriptive variable names, and adds comments to clarify the purpose of each section. It will make your code more organized, readable, and maintainable.Brief description of changes

archive/streamlit_app.py

@@ -1,13 +1,10 @@
-import string
-import spacy
-import pywaffle
 import streamlit as st
 import pandas as pd
 import json
 import plotly.express as px
 import plotly.graph_objects as go
 import matplotlib.pyplot as plt
-import squarify
+import pywaffle
 
 st.title('Resume :blue[Matcher]')
 st.image('Assets/img/header_image.jpg')
@@ -20,82 +17,68 @@ def read_json(filename):
     return data
 
 
-# read the json file
-resume = read_json(
-    'Data/Processed/Resume-d531571e-e4fa-45eb-ab6a-267cdeb6647e.json')
-job_desc = read_json(
-    'Data/Processed/Job-Desc-a4f06ccb-8d5a-4d0b-9f02-3ba6d686472e.json')
-
-st.write("### Reading Resume's POS")
-df = pd.DataFrame(resume['pos_frequencies'], index=[0])
-fig = go.Figure(data=go.Bar(y=list(resume['pos_frequencies'].values()), x=list(resume['pos_frequencies'].keys())),
-                layout_title_text="Resume's POS")
-st.write(fig)
-
-df2 = pd.DataFrame(resume['keyterms'], columns=["keyword", "value"])
-st.dataframe(df2)
-
-# Create the dictionary
-keyword_dict = {}
-for keyword, value in resume['keyterms']:
-    keyword_dict[keyword] = value
-
-fig = go.Figure(data=[go.Table(header=dict(values=["Keyword", "Value"],
-                                           font=dict(size=12),
-                                           fill_color='#070A52'),
-                               cells=dict(values=[list(keyword_dict.keys()),
-                                                  list(keyword_dict.values())],
-                                          line_color='darkslategray',
-                                          fill_color='#6DA9E4'))
-                      ])
-st.plotly_chart(fig)
-
-st.divider()
-
-for keyword, value in resume['keyterms']:
-    pass
-
-
-# display the waffle chart
-figure = plt.figure(
-    FigureClass=pywaffle.Waffle,
-    rows=20,
-    columns=20,
-    values=keyword_dict,
-    legend={'loc': 'upper left', 'bbox_to_anchor': (1, 1)})
-
-
-# Display the dictionary
-
-st.pyplot(fig=figure)
-# st.write(dict)
-
-fig = px.treemap(df2, path=['keyword'], values='value',
-                 color_continuous_scale='RdBu',
-                 title='Resume POS')
-st.write(fig)
-
-
-st.plotly_chart(figure_or_data=fig)
-
-fig = go.Figure(data=[go.Table(
-    header=dict(values=["Tri Grams"],
-                fill_color='#1D267D',
-                align='center', font=dict(color='white', size=16)),
-    cells=dict(values=[resume['tri_grams']],
-               fill_color='#19A7CE',
-               align='left'))])
-
-st.plotly_chart(figure_or_data=fig)
-
-fig = go.Figure(data=[go.Table(
-    header=dict(values=["Bi Grams"],
-                fill_color='#1D267D',
-                align='center', font=dict(color='white', size=16)),
-    cells=dict(values=[resume['bi_grams']],
-               fill_color='#19A7CE',
-               align='left'))])
-
-st.plotly_chart(figure_or_data=fig)
-
-
+def main():
+    resume = read_json('Data/Processed/Resume-d531571e-e4fa-45eb-ab6a-267cdeb6647e.json')
+    job_desc = read_json('Data/Processed/Job-Desc-a4f06ccb-8d5a-4d0b-9f02-3ba6d686472e.json')
+
+    show_pos(resume)
+    show_keyterms(resume)
+    show_waffle_chart(resume['keyterms'])
+    show_treemap(resume['keyterms'])
+    show_n_grams(resume['tri_grams'], 'Tri Grams')
+    show_n_grams(resume['bi_grams'], 'Bi Grams')
+
+
+def show_pos(resume_data):
+    st.write("### Reading Resume's POS")
+    df = pd.DataFrame(resume_data['pos_frequencies'], index=[0])
+    fig = go.Figure(data=go.Bar(y=list(resume_data['pos_frequencies'].values()), x=list(resume_data['pos_frequencies'].keys())),
+                    layout_title_text="Resume's POS")
+    st.plotly_chart(fig)
+
+
+def show_keyterms(resume_data):
+    df2 = pd.DataFrame(resume_data['keyterms'], columns=["keyword", "value"])
+    st.dataframe(df2)
+    fig = go.Figure(data=[go.Table(header=dict(values=["Keyword", "Value"],
+                                               font=dict(size=12),
+                                               fill_color='#070A52'),
+                                   cells=dict(values=[list(keyword_dict.keys()),
+                                                      list(keyword_dict.values())],
+                                              line_color='darkslategray',
+                                              fill_color='#6DA9E4'))
+                          ])
+    st.plotly_chart(fig)
+
+
+def show_waffle_chart(keyword_dict):
+    figure = plt.figure(
+        FigureClass=pywaffle.Waffle,
+        rows=20,
+        columns=20,
+        values=keyword_dict,
+        legend={'loc': 'upper left', 'bbox_to_anchor': (1, 1)})
+    st.pyplot(fig=figure)
+
+
+def show_treemap(keyword_data):
+    df2 = pd.DataFrame(keyword_data, columns=["keyword", "value"])
+    fig = px.treemap(df2, path=['keyword'], values='value',
+                     color_continuous_scale='RdBu',
+                     title='Resume POS')
+    st.plotly_chart(fig)
+
+
+def show_n_grams(n_gram_data, title):
+    fig = go.Figure(data=[go.Table(
+        header=dict(values=[title],
+                    fill_color='#1D267D',
+                    align='center', font=dict(color='white', size=16)),
+        cells=dict(values=[n_gram_data],
+                   fill_color='#19A7CE',
+                   align='left'))])
+    st.plotly_chart(figure_or_data=fig)
+
+
+if __name__ == "__main__":
+    main()

run_first.py

@@ -1,60 +1,37 @@
 import json
+import logging
 from scripts.utils.ReadFiles import get_filenames_from_dir
 from scripts.ResumeProcessor import ResumeProcessor
 from scripts.JobDescriptionProcessor import JobDescriptionProcessor
-import logging
 
-logging.basicConfig(filename='app.log', filemode='w',
-                    level=logging.DEBUG,
+logging.basicConfig(filename='app.log', filemode='w', level=logging.DEBUG,
                     format='%(name)s - %(levelname)s - %(message)s')
 
-
 def read_json(filename):
     with open(filename) as f:
         data = json.load(f)
     return data
 
-
-logging.info('Started to read from Data/Resumes')
-try:
-    # Check if there are resumes present or not.
-    # If present then parse it.
-    file_names = get_filenames_from_dir("Data/Resumes")
-    logging.info('Reading from Data/Resumes is now complete.')
-except:
-    # Exit the program if there are no resumes.
-    logging.error('There are no resumes present in the specified folder.')
-    logging.error('Exiting from the program.')
-    logging.error(
-        'Please add resumes in the Data/Resumes folder and try again.')
-    exit(1)
-
-# Now after getting the file_names parse the resumes into a JSON Format.
-logging.info('Started parsing the resumes.')
-for file in file_names:
-    processor = ResumeProcessor(file)
-    success = processor.process()
-logging.info('Parsing of the resumes is now complete.')
-
-logging.info('Started to read from Data/JobDescription')
-try:
-    # Check if there are resumes present or not.
-    # If present then parse it.
-    file_names = get_filenames_from_dir("Data/JobDescription")
-    logging.info('Reading from Data/JobDescription is now complete.')
-except:
-    # Exit the program if there are no resumes.
-    logging.error(
-        'There are no job-description present in the specified folder.')
-    logging.error('Exiting from the program.')
-    logging.error(
-        'Please add resumes in the Data/JobDescription folder and try again.')
-    exit(1)
-
-# Now after getting the file_names parse the resumes into a JSON Format.
-logging.info('Started parsing the Job Descriptions.')
-for file in file_names:
-    processor = JobDescriptionProcessor(file)
-    success = processor.process()
-logging.info('Parsing of the Job Descriptions is now complete.')
-logging.info('Success now run `streamlit run streamlit_second.py`')
+def process_files(directory_path, processor_class):
+    try:
+        file_names = get_filenames_from_dir(directory_path)
+        logging.info(f'Reading from {directory_path} is now complete.')
+    except:
+        logging.error(f'There are no files present in {directory_path}.')
+        logging.error('Exiting from the program.')
+        logging.error(f'Please add files in the {directory_path} folder and try again.')
+        exit(1)
+
+    logging.info(f'Started processing files in {directory_path}.')
+    for file in file_names:
+        processor = processor_class(file)
+        success = processor.process()
+    logging.info(f'Processing of files in {directory_path} is now complete.')
+
+if __name__ == "__main__":
+    try:
+        process_files("Data/Resumes", ResumeProcessor)
+        process_files("Data/JobDescription", JobDescriptionProcessor)
+        logging.info('Success! Run `streamlit run streamlit_second.py`')
+    except Exception as e:
+        logging.error(f'An error occurred: {str(e)}')