Pandas Jobs

I’m sitting on large, messy numeric datasets and need them cleaned, engineered, and split so downstream models train smoothly. Your mission is to design a reproducible preprocessing pipeline: audit the raw CSVs, tackle missing or extreme values, scale or normalize where it counts, generate meaningful features, and output train/validation/test sets ready for model development. Python with pandas, NumPy, and scikit-learn is my default tech stack, but feel free to weave in any modern data-ops tricks—as long as the final workflow runs inside a Docker container that can drop into our CI pipeline. Deliverables • Clean, documented datasets (CSV or Parquet) • Version-controlled preprocessing scripts/notebooks • Dockerfile plus a concise README for one-command rep...

I’m preparing a predictive analytics initiative for a finance-focused dataset stored in traditional relational tables and well-formatted spreadsheets. The core objective is to turn this structured historical information into forward-looking insights—think probability scores for default, churn, or other key risk and revenue indicators. You will take ownership of the full machine-learning pipeline: data ingestion from CSV/SQL sources, exploratory analysis, feature engineering, model selection and training, validation, and a concise performance report. I expect reproducible Python code (preferably using pandas, scikit-learn, XGBoost or similar), clear comments, and a short write-up that explains both the methodology and how to refresh the model with new data. Deliverables: &bull...

# Collaboration Opportunity: SafeLink AI **Project:** Explainable Phishing and Scam Message Detector **Duration:** 7–14 days **Collaboration type:** Unpaid academic / portfolio collaboration **Technology:** Python, Pandas, scikit-learn, Streamlit, Joblib, Git/GitHub ## 1. Project overview I am developing SafeLink AI as a college group experiential learning project. The objective is to build a simple web application that analyses text messages, predicts whether a message belongs to the classes supported by the selected dataset, highlights observable warning indicators, and provides general safety guidance. I already have a detailed project proposal explaining the objectives, scope, methodology, mathematical logic component, evaluation metrics, and expected deliverables. I am...

I need a Python-driven analysis of my market research data to pinpoint our ideal target audience. The raw survey and demographic files are already compiled; what I’m missing is a clear, data-backed profile that we can hand off to marketing and product teams. Here is what I expect: • Clean and structure the datasets so they’re ready for analysis. • Run exploratory data analysis and any relevant statistical tests or clustering to surface audience segments. • Translate the findings into a concise executive summary with charts and actionable insights. You are free to use pandas, NumPy, scikit-learn, or similar libraries, provided the final notebook or script is well-commented and reproducible. I’ll supply the data and be available for quick clarifications alo...

For my portfolio, I want to develop a complete Python data-science walkthrough based on a public healthcare dataset. The work should start with careful data cleaning (handling missing values, outliers, type conversions) and move through exploratory analysis before arriving at polished visual insights created with pandas, NumPy and Matplotlib. After the EDA, I would like you to implement at least one simple machine-learning model that suits the data—classification, regression or clustering—so feel free to choose whichever fits best once you have explored the variables and target. Please keep the modelling lightweight and well-commented so another student can easily follow the logic. Deliverables • Jupyter notebook (.ipynb) containing all code, visualisations and nar...

I’m working with a raw financial dataset and I need it taken from “messy” to “decision-ready.” The core goal is to surface meaningful trends, so every step—from preparation through visualization—must support that objective. You’ll start by importing the data into Excel or a SQL environment and normalizing the fields so they’re analysis-ready. Once the structure is consistent, feel free to apply Python (Pandas, NumPy, matplotlib/seaborn) for deeper profiling and any additional quality checks you find useful. When the numbers line up, shift the focus to insight generation: uncover the key trend lines, seasonality patterns, or shifts that matter to stakeholders. The polished story should appear in Power BI: an interactive dashboard with ...

Sales Performance Analysis: Summary 1. Overview End-to-end data analytics project using Python, SQL, and Power BI Dataset: Superstore sales data, about 9,800 records Covers orders, customers, products, regions, and shipping Goal: turn raw sales data into clear business insights 2. Process Cleaned the data in Python (Pandas): fixed missing values, duplicates, and data types Created new features: shipping days, month, quarter, and season Explored the data with EDA in Python Queried the data with SQL to answer business questions Compared performance across regions, categories, segments, and time periods 3. Dashboard and Findings Interactive, dark-themed Power BI dashboard Filters for year, region, and category Key results: $2.26M total sales 5K orders and 793 customers West is the top reg...

I have a collection of forms saved only as scanned‐image PDFs. I need every piece of readable text lifted from those images and placed neatly into an Excel workbook. The end file should let me filter, sort, and analyse the information just as if it had been typed there originally. Because the source files are images, reliable OCR will be essential. You may use Adobe Acrobat, Tesseract, Python (pandas, openpyxl) or any other toolchain you prefer, as long as the final spreadsheet is clean and ready for immediate use. Deliverables: • One .xlsx file containing the extracted text, organised consistently across all forms • A brief note on the method you used (software or script) so I can reproduce the process if new forms arrive later Accuracy matters more than speed; I will spo...

I’m sitting on a CSV/Excel dataset of roughly 200,000 Glasgow real-estate listings. Each record already carries a free-text property description, but nothing else has been standardised or verified yet. What I need now is a thorough data-clean-up and structuring pass so the file becomes immediately usable for analysis, dashboards, or import into a database later on. Core tasks • Load the Excel/CSV, remove obvious duplicates and empty rows • Parse and normalise key fields you can extract from the descriptions (e.g., bedrooms, property type, postcode, square footage if present) – the richer the capture, the better • Flag listings with missing critical info so I can review them quickly • Deliver a final, well-formatted CSV/Excel plus a short summary...

I have a collection of numerical datasets and I’d like a well-structured Python workflow that lets me explore, clean, visualise and extract clear insights from them. The scope covers everything from loading raw files through to producing a set of summary statistics, meaningful charts and a concise write-up of the findings. Quality matters more to me than speed, so feel free to propose thoughtful approaches—whether it’s a classic pandas / NumPy pipeline, more advanced SciPy techniques or even light machine-learning models if they add value. I’ll supply the data and clarify any domain specifics once we start. Deliverables I expect: • Fully commented Python code (Jupyter Notebook or .py) • Cleaned dataset ready for future work • Visualisation...