NumPy Jobs

I’ve collected a sizable housing-market dataset and now need a complete prediction pipeline built in Python. The work starts with thorough cleaning, preprocessing, and creative feature engineering so that every useful signal—size, rooms, location ratings, and any other attributes we can derive—is captured. Once the dataset is ready, I want to benchmark several approaches, but the core focus is Random Forest Regression. Feel free to test Linear or Support Vector methods if they might edge out the forest, yet the final report should clearly show how each model performs against the usual metrics (RMSE, MAE, R²). Visual insight is important, so the notebook or script has to generate intuitive plots—scatter trends, residual diagnostics, whatever best tells the sto...

I need a simple Streamlit dashboard built in Python that loads data from a numpy .npz file and displays investment analysis charts. The dashboard should run locally with streamlit run app.py. What I need: 5 pages using Streamlit multi-page routing. Each page shows metrics and 2-3 Plotly charts for a different asset. The charts are: IRR probability distribution (histogram/KDE), DSCR by year (bar chart), and a scenario comparison (horizontal bar chart). One sidebar with a scenario dropdown that updates the charts. Tech stack: Python, Streamlit, Plotly, numpy. No database, no authentication, no deployment needed. Desktop only. Data: I will provide a .npz file with pre-computed numpy arrays (IRR distributions, DSCR arrays, scenario values). I will give you the exact key names and shapes. You j...

I have a set of raw financial data that I need cleaned, explored, and transformed into clear trend insights. The job is squarely in the Data Analysis space, and Python is the language I want everything built in. Here is what I’m after: • Import and tidy the financial data (CSV and/or Excel). • Run a thorough Trend Analysis—identify seasonality, growth or decline patterns, and any statistically significant shifts over time. • Produce easy-to-read visualizations (Matplotlib, Seaborn or Plotly are all fine) and a concise narrative summary of your findings. I’ll consider the work complete when I receive: 1. Well-commented Python scripts or Jupyter Notebook that reproduces the analysis end-to-end. 2. The generated charts in PNG or embedded in the...

I’m ready to turn my existing options-buying strategy into a fully automated Python system that places live orders through Zerodha Kite Connect. The core logic is already defined; what I need now is a clean, production-ready codebase that can: • Translate my entry and exit rules into trade signals for option contracts • Fire market or limit orders instantly via the Kite API, handling throttling, errors, and reconnections gracefully • Stream live P&L, Greeks, and position data to a lightweight dashboard or terminal view so I can supervise performance in real time • Run historical backtests on minute-level data to validate tweaks before they go live, outputting metrics like win rate, drawdown, and expectancy I value readable, modular code (separate data,...

I have a collection of CSV and Excel files filled with purely numerical columns that I need turned into clear, actionable insight. Your task is to take these raw tables all the way from initial cleaning through to a succinct set of findings, visualisations and recommendations that I can present to non-technical stakeholders. The workflow I expect is straightforward: import the files, tidy up missing or inconsistent values, run the exploratory statistics that uncover patterns or anomalies, then build concise plots (Python / pandas / NumPy / Matplotlib or similar) so the story of the data is obvious at a glance. If meaningful, a simple predictive model or correlation analysis would be welcome as well, but only if it genuinely adds value. Deliverables • A reproducible notebook or scr...

I need a concise software tool that reads one-or-multiple CSV or Excel workbooks, runs a set of statistical analyses, and returns clean, ready-to-share results. The primary work is software engineering; the database portion is strictly file-based, so no SQL servers are involved. Core workflow 1. User selects or drops the CSV/XLSX files. 2. The program performs descriptive statistics (mean, median, variance, standard deviation), correlation matrices, and any other common tests you recommend. 3. Results are exported to a new Excel sheet, PDF, or JSON summary—whatever is simplest to reuse. Tech stack is your call, but Python (pandas, NumPy, SciPy) or a lightweight C#/.NET implementation would suit the environment here. The code must be: • Fully commented and modular s...

- Developed ChurnShield, an end-to-end AI-powered platform for customer churn prediction and retention intelligence, utilizing Python, FastAPI, TensorFlow, and Streamlit. - Created a custom Artificial Neural Network (ANN) featuring three dense layers, batch normalization, dropout regularization, early stopping, and Adam optimization for churn prediction. - Implemented industry-specific machine learning pipelines for telecommunications and banking datasets, incorporating automated preprocessing and feature engineering. - Established intelligent churn risk classification systems that categorize customers into high, medium, and low-risk groups based on probability scoring. - Designed an interactive, cyberpunk-inspired analytics dashboard for real-time KPI monitoring, risk segmentation, cu...