Spaces:
Sleeping
Sleeping
| import PyPDF2 | |
| from docx import Document | |
| from pptx import Presentation | |
| from nlp import get_average_similarity_scores | |
| import numpy as np | |
| import plotly.graph_objects as go | |
| import os | |
| import tempfile | |
| import shutil | |
| # Langchain document loaders | |
| from langchain.document_loaders import PyPDFLoader #for pdf files | |
| from langchain.document_loaders import TextLoader #for text files | |
| from langchain.document_loaders import Docx2txtLoader #for docx files | |
| from langchain.document_loaders import UnstructuredPowerPointLoader #for pptx files | |
| from constants import StreamlitException | |
| from PyPDF2.errors import PdfReadError | |
| from zipfile import BadZipFile | |
| def load_file(st, uploaded_file): | |
| # uploaded_file is the output of st.sidebar.file_uploader | |
| file_type = uploaded_file.type | |
| try: | |
| os.mkdir('downloaded_files') | |
| except FileExistsError: | |
| pass | |
| download_path = os.path.join('downloaded_files', uploaded_file.name) | |
| with tempfile.NamedTemporaryFile(delete=False) as tmp_file: | |
| # Write the contents of the uploaded file to the temporary file | |
| tmp_file.write(uploaded_file.read()) | |
| tmp_file.flush() | |
| shutil.copy(tmp_file.name, download_path) | |
| try: | |
| if file_type == "application/pdf": | |
| resume_text_raw = extract_pdf_text(uploaded_file) | |
| lang_loader = PyPDFLoader(download_path) | |
| elif file_type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document": | |
| resume_text_raw = extract_word_text(uploaded_file) | |
| lang_loader = Docx2txtLoader(download_path) | |
| elif file_type == "application/vnd.ms-powerpoint" or file_type == "application/vnd.openxmlformats-officedocument.presentationml.presentation": | |
| resume_text_raw = extract_ppt_text(uploaded_file) | |
| lang_loader = UnstructuredPowerPointLoader(download_path) | |
| else: | |
| return StreamlitException("**Error**: Invalid file format. Please upload a Word, PDF, or PowerPoint file.") | |
| except (PdfReadError, BadZipFile): | |
| return StreamlitException("**Error**: Invalid file content. Please upload a valid Word, PDF, or PowerPoint file.") | |
| return resume_text_raw, lang_loader | |
| # Function to extract text from a PDF file | |
| def extract_pdf_text(file): | |
| pdf_reader = PyPDF2.PdfReader(file) | |
| text = "" | |
| for page in pdf_reader.pages: | |
| lines = page.extract_text().split('\n') | |
| for line in lines: | |
| text += line.strip() + ".\n" | |
| return text | |
| # Function to extract text from a Word file | |
| def extract_word_text(file): | |
| doc = Document(file) | |
| text = '' | |
| p_iter = iter(doc.paragraphs) | |
| t_iter = iter(doc.tables) | |
| while True: | |
| try: | |
| paragraph = next(p_iter) | |
| text += paragraph.text + '.\n' | |
| except StopIteration: | |
| break | |
| try: | |
| table = next(t_iter) | |
| for row in table.rows: | |
| for cell in row.cells: | |
| text += cell.text + '\t' | |
| text += '\n' | |
| except StopIteration: | |
| pass | |
| return text | |
| # Function to extract text from a PowerPoint file | |
| def extract_ppt_text(file): | |
| prs = Presentation(file) | |
| text = "" | |
| for slide in prs.slides: | |
| for shape in slide.shapes: | |
| if shape.has_text_frame: | |
| text += shape.text_frame.text | |
| return text | |
| # Function to plot the average similarity score for each job description phrase | |
| def plot_similarity_scores(job_description_phrases, resume_phrases): | |
| avg_similarity_scores = get_average_similarity_scores(job_description_phrases, resume_phrases) | |
| sorted_scores = sorted(enumerate(avg_similarity_scores), key=lambda x: x[1], reverse=True)[:10] | |
| indices = [i[0] for i in sorted_scores] | |
| sorted_scores = [i[1] for i in sorted_scores] | |
| y_pos = list(range(len(indices))) | |
| fig = go.Figure() | |
| fig.add_trace(go.Bar( | |
| y=y_pos, | |
| x=sorted_scores, | |
| orientation='h' | |
| )) | |
| fig.update_layout( | |
| yaxis=dict( | |
| tickmode="array", | |
| tickvals=y_pos, | |
| ticktext=[s[:100].ljust(100) + '...' if len(s) > 100 else s.ljust(75) for s in np.array(job_description_phrases)[indices]], | |
| tickfont=dict(size=14), | |
| autorange="reversed", | |
| side="right", | |
| automargin=True | |
| ), | |
| xaxis=dict( | |
| tickmode="array", | |
| tickvals=np.round(np.arange(0, 1.2, 0.2), 2), | |
| ticktext=np.round(np.arange(0, 1.2, 0.2), 2), | |
| tickfont=dict(size=14), | |
| range=[0, 1.05] | |
| ), | |
| showlegend=False, | |
| margin=dict(t=0) | |
| ) | |
| fig.update_xaxes(title="Average Similarity Score", title_font=dict(size=14)) | |
| return fig |