Projects using Python in KathmanduProjects using Python in Kathmandu
Cover image for Python Chatbot Using Cosine Similarity
I
Python Chatbot Using Cosine Similarity I built a Python-based chatbot that uses cosine similarity to compare text and identify the closest matching response. The project explores text similarity, vector-based comparison, and conversational interaction, demonstrating how mathematical techniques can be applied to build a simple chatbot. Key Features Text similarity matching: Uses cosine similarity to compare text representations. Response selection: Identifies the closest matching candidate based on similarity scores. Python development: Implements the chatbot's matching logic using Python. Applied mathematics: Uses vector similarity to compare text representations. Technical Approach Cosine similarity measures the angle between two vectors to estimate how closely they align. When combined with an appropriate text vectorization method, it can help a chatbot match user messages with relevant stored responses. Technologies Python · Natural Language Processing (NLP) · Cosine Similarity Project Source View the project on GitHub (https://github.com/ak-Machine-Learning/Chatbot)
0
72
Cover image for Brands kept asking me for
Brands kept asking me for UGC creators. So I stopped doing it manually. I built an automation that finds creators, stores their data, and pulls their emails — all without spending a cent on tools like Apollo or any paid APIs. No bans. No API costs. Just pure leverage. Scraped 10K+ creators with verified emails in just 10 days. This is what contra work looks like when you build your own systems. 👇 Watch how it works.
0
94
Cover image for Brand Fill Loader: your logo
Brand Fill Loader: your logo is the loader. Drop in any logo and it fills up like liquid while a rolling counter climbs to 100%, then the logo pops and a check badge lands. It is made for SaaS upload, export and onboarding screens, where a generic spinner would normally sit. To rebrand it, replace one logo image, retype three texts (status, done message, brand name) and change two colors. The second brand in the video (Nimbus Pay) was made through the SVGator MCP in six edits. Named layers: logo, status-text, status-done, brand-name, progress-bar, badge-bg, percent. Motion designed in code, project built and rebranded through the SVGator MCP, then checked in the SVGator editor. X post: https://x.com/sabinm47/status/2112050094589751574
5
2
356
Cover image for My first post here on Contra! A project from last year that ...
My first post here on Contra! A project from last year that I really enjoyed working on: Style Transfer using Transformers. The identity was inspired by mountains, factories, and the shared effort behind every great piece of art. The goal was to blend structural integrity with artistic styles, transforming everyday scenes into visually striking pieces while preserving their core essence. I leveraged Transformer-based architectures to achieve arbitrary style transfer, experimenting with different styles and datasets to create diverse outputs. This project challenged me to combine technical rigor with creative exploration, and it’s one of my favorite projects because of how the results turned out. Excited to start sharing more of my work here 🙌 and looking forward to connecting with other creators and enthusiasts!
0
57
Cover image for Sentiment Analysis Using Machine Learning
Sentiment Analysis Using Machine Learning and Deep Learning I developed a text-classification project to compare traditional machine learning algorithms with a deep learning model for sentiment analysis. The project covers text preprocessing, feature extraction, model training, performance evaluation, and saving trained models for reuse. What I Built Text preprocessing: Prepared review text for model training. Feature extraction: Used TF-IDF for traditional machine learning models and tokenized sequences for the GRU model. Model comparison: Evaluated Logistic Regression, Multinomial Naive Bayes, Linear SVM, Random Forest, and GRU. Performance evaluation: Generated classification reports and visualizations to compare model results. Model persistence: Saved trained models and preprocessing components for reuse. Tech Stack Python · Pandas · NumPy · Scikit-learn · TensorFlow/Keras · NLP · TF-IDF · Matplotlib · Joblib What This Project Demonstrates This project gave me practical experience building and evaluating NLP pipelines, comparing different modelling approaches, and examining how model choice affects text-classification performance. Source Code View the project on GitHub (https://github.com/ak-Machine-Learning/Sentiment-Analysis-Model-Comparison)
2
240