Krishan Bijarniya

• Languages: Python (Advanced), SQL (SQLite/MySQL), HTML/CSS.
• Data Science: Pandas, NumPy, Scikit-Learn, TensorFlow/Keras, NLTK, OpenCV.
• Data Engineering: Web Scraping (BeautifulSoup/Selenium), OCR (Tesseract), Regex, PDF Automation (Tabula/pdfplumber).
• Visualization: Matplotlib, Seaborn, Power BI, Tableau.
• Developer Tools: VS Code, Jupyter Notebook, Git/GitHub, Eel (GUI).

Auratech Services | Data Analyst Intern Jaipur, Rajasthan | Dec 2023 – July 2024 * Database Management: Developed and maintained company database systems, ensuring 100% data integrity and accessibility for stakeholders.

• Data Cleaning & Quality: Engineered automated cleaning pipelines using Python (Pandas) to rectify inconsistencies, reducing data errors by 40%.
• Reporting: Utilized SQL for complex querying and Python for data manipulation to generate automated business reports and visual insights.

Omni-Extract: Offline Data Extraction Engine | Python, Eel, OCR

• Developed a desktop application to automate data extraction from PDFs and Handwritten images.
• Integrated Tesseract OCR and pdfplumber to digitize messy financial records securely offline.

Blackcoffer Data Extraction & NLP | Python, BeautifulSoup, NLTK

• Engineered a pipeline to scrape 100+ URLs and perform sentiment analysis.
• Manually calculated Fog Index and Polarity Scores for high-precision readability metrics.

Email Spam Classification System | Machine Learning, Scikit-Learn

• Built a text classification model using Random Forest and CountVectorizer.
• Achieved 95% Accuracy in identifying and filtering unsolicited communications.

JustDial Business Lead Scraper | Python, Requests, Regex

• Automated the extraction of B2B leads from public directories.
• Used Regex to sanitize HTML and format data for direct Excel/SQL export.