Tag: Python
-
Textual Genres Analysis using the Carloto’s NLP Algorithm

Featured Photo by Dominika Roseclay on Pexels. Computational Linguistics (CL) is the scientific study of language. Oftentime, CL is linked to the Python software development based on Natural Language Processing (NLP) libraries. NLP basically consists of combining machine learning (ML) techniques with text, and using math and statistics to get that text in a format…
-
A Comparison of Scikit Learn Algorithms for Breast Cancer Classification – 2. Cross Validation vs Performance

The post is a continuation of a previous breast cancer study comparing Scikit-Learn binary classifiers for cross validation and model performance. The classifiers compared include Logistic Regression, GaussianNB, SVC, KNN, Random Forest, Extra Trees, and Gradient Boosting. Learning curves show the comparison of classifier performance. Results indicate GaussianNB is more efficient than SVC in terms…
-
A Comparison of Binary Classifiers for Enhanced ML/AI Breast Cancer Diagnostics – 1. Scikit-Plot

The post compares binary classifiers in Scikit-Learn using the breast cancer dataset. It includes data analysis, ML preparation, learning curves, feature dominance, calibration curves, confusion matrix, ROC curve, precision-recall curve, KS statistic, cumulative gains, lift curves, PCA, and classification reports. Various models’ performances are compared with focus on key metrics and feature evaluations.
-
Build A Simple NLP/NLTK Chatbot

Chatbots are computer programs that automate conversations with users, providing real-time customer support and industry-specific solutions. This example demonstrates creating a chatbot using Python within Jupyter IDE and implementing simple dialogue. Chatbots are widely used in digital marketing for various business applications, such as customer service, sales, FAQ, shopping, and marketing.
-
DOGE-INR Price Prediction Backtesting

Featured Photo by Rūdolfs Klintsons Let’s look at the Dogecoin: Dogecoin is trading at 0.0666 as of the 13th of March 2023, a 0.91% increase since the beginning of the trading day. Dogecoin has 54 percent odds of going through some form of financial distress in the next two years and has generated negative returns to investors over the last 90…
-
Hands-On USGS Webscraping of Earthquakes- Worldwide (24 Hours)

A live global earthquake tracker has been developed using the USGS earthquake data feed. This tool, which functions 24/7, distinguishes between underground nuclear explosions and organic or man-made seismic activities such as earthquakes and mining explosions. This tracker is crucial given that a third of the world’s population is exposed to earthquakes.
-
The $ASML Trading Strategies via the Plotly Stock Market Dashboard

Dr. Dividend has shared an insight into a stock market analysis using Plotly’s interactive Stock Market Dashboard. The rundown explains how to fetch live data using yfinance API, create visuals incorporating moving averages, and craft multiple trading signals, including the use of the MACD and Stochastic Oscillator. The tutorial also guides on saving the final…
-
ML/AI Breast Cancer Diagnosis with 98% Confidence

We demonstrate the importance of hyperparameter optimization (HPO) for enhancing ML prediction accuracy. Specifically, we will focus on the Random Forest Classifier (RFC) as an ensemble of decision trees. RFC is a supervised ML algorithm that has been applied successfully to the BC binary classification.
-
Breast Cancer ML Classification – Logistic Regression vs Gradient Boosting with Hyperparameter Optimization (HPO)

Breast Cancer (BC) is the leading cause of death among women worldwide. The present study optimizes the use of supervised Machine Learning (ML) algorithms for detecting, analyzing, and classifying BC. We compare Logistic Regression (LR) against Gradient Boosting (GB) Classifier within the Hyperparameter Optimization (HPO) loop given by GridSearchCV. We use the publicly available BC dataset…
-
BTC-USD Price Prediction with LSTM

The objective of this project is to test the deep learning algorithm of real-time BTC-USD price prediction. We trained the 2-layers Long Short Term Memory Neural Network using Bitcoin Historical Data. The trained LSTM model can be used to predict future price movements of bitcoin. RMSE ~ $64, with the mean price of $20k (Oct…
-
A Comparative Analysis of Breast Cancer ML/AI Binary Classifications

This study is dedicated to #BreastCancerAwarenessMonth2022 #breastcancer #BreastCancerDay @Breastcancerorg @BCAction @BCRFcure @NBCF @LivingBeyondBC @breastcancer @TheBreastCancer @thepinkribbon @BreastCancerNow. One of the most common cancer types is breast cancer (BC), and early diagnosis is the most important thing in its treatment. Recent studies have shown that BC can be accurately predicted and diagnosed using machine learning (ML) technology. Our…
-
A Comparison of ML/AI Diabetes-2 Binary Classification Algorithms

The post discusses the increasing urgency to diagnose and treat Type-2 Diabetes (T2D), particularly in developing nations. It delves into the use of data-driven techniques, including ML/AI, in processing T2D data. Different ML/AI methods including DNN, SVM, and DT are applied to the Kaggle PIMA Indian Diabetes (PID) dataset, and performance is assessed using Python…
-
Bear vs. Bull Portfolio Risk/Return Optimization QC Analysis

Based on the Portfolio Allocation and Optimization Algorithm discussed earlier and the related portfolio management, let’s run the Bear vs. Bull QC test of the portfolio P=[MSFT, AAPL, NDAQ] in terms of the Risk/Return Ratio (RRR). We have got a Sharpe ratio of less than one that is considered unacceptable or bad. The risk the…
-
HPO-Tuned ML Diabetes-2 Prediction

The blog details the author’s tests with machine learning (ML) for enhanced prediction of Type-2 diabetes. The workflows used include RandomizedSearchCV HPO, accuracy metrics, and cross-validation. The post provides in-depth analysis and comparisons of different ML algorithms, such as RandomForestClassifier, GaussianNB, and DecisionTreeClassifier. The experiment findings indicate that RandomForestClassifier with RandomizedSearchCV provides the highest accuracy,…
-
Portfolio Optimization Risk/Return QC – Positions of Humble Div vs Dividend Glenn

The Portfolio Optimization Algorithm (POA) is used for comparing the top five stock positions of Humble Div (HD) and Dividend Glenn (DG) from 2017 to 2022. The Risk/Return Ratio (RRR) shows HD portfolio as a better performer than DG portfolio and the market. Both portfolios and market are within risk boundaries.
-
Risk/Return QC via Portfolio Optimization – Current Positions of The Dividend Breeder

Featured Image by AbsolutVision on Unsplash Based on the Portfolio Optimization Algorithm (POA) discussed earlier, let’s run the QC test of current positions of The Dividend Breeder in terms of the Risk/Return Ratio (RRR). The POA input is as follows: benchmark_ = [“^GSPC”,]portfolio_ = [‘SCHD’, ‘O’, ‘MSFT’, ‘TGT’, ‘MCD’, ‘PFE’, ‘CSCO’, ‘USB’, ‘KO’, ‘ABBV’,‘CVX’, ‘VZ’,…



