Showing results for Shared Product Vector
GitHub Repo
https://github.com/lucaLP98/Parallel_vector_matrix_product_OpenMP
lucaLP98/Parallel_vector_matrix_product_OpenMP
Calculating the matrix-vector product on a shared memory MIMD machine, using the OpenMP library.
GitHub Repo
https://github.com/Jai-Agarwal-04/Sentiment_Analysis_with_Insights
Jai-Agarwal-04/Sentiment_Analysis_with_Insights
Sentiment Analysis with Insights using NLP and Dash This project show the sentiment analysis of text data using NLP and Dash. I used Amazon reviews dataset to train the model and further scrap the reviews from Etsy.com in order to test my model. Prerequisites: Python3 Amazon Dataset (3.6GB) Anaconda How this project was made? This project has been built using Python3 to help predict the sentiments with the help of Machine Learning and an interactive dashboard to test reviews. To start, I downloaded the dataset and extracted the JSON file. Next, I took out a portion of 7,92,000 reviews equally distributed into chunks of 24000 reviews using pandas. The chunks were then combined into a single CSV file called balanced_reviews.csv. This balanced_reviews.csv served as the base for training my model which was filtered on the basis of review greater than 3 and less than 3. Further, this filtered data was vectorized using TF_IDF vectorizer. After training the model to a 90% accuracy, the reviews were scrapped from Etsy.com in order to test our model. Finally, I built a dashboard in which we can check the sentiments based on input given by the user or can check the sentiments of reviews scrapped from the website. What is CountVectorizer? CountVectorizer is a great tool provided by the scikit-learn library in Python. It is used to transform a given text into a vector on the basis of the frequency (count) of each word that occurs in the entire text. This is helpful when we have multiple such texts, and we wish to convert each word in each text into vectors (for using in further text analysis). CountVectorizer creates a matrix in which each unique word is represented by a column of the matrix, and each text sample from the document is a row in the matrix. The value of each cell is nothing but the count of the word in that particular text sample. What is TF-IDF Vectorizer? TF-IDF stands for Term Frequency - Inverse Document Frequency and is a statistic that aims to better define how important a word is for a document, while also taking into account the relation to other documents from the same corpus. This is performed by looking at how many times a word appears into a document while also paying attention to how many times the same word appears in other documents in the corpus. The rationale behind this is the following: a word that frequently appears in a document has more relevancy for that document, meaning that there is higher probability that the document is about or in relation to that specific word a word that frequently appears in more documents may prevent us from finding the right document in a collection; the word is relevant either for all documents or for none. Either way, it will not help us filter out a single document or a small subset of documents from the whole set. So then TF-IDF is a score which is applied to every word in every document in our dataset. And for every word, the TF-IDF value increases with every appearance of the word in a document, but is gradually decreased with every appearance in other documents. What is Plotly Dash? Dash is a productive Python framework for building web analytic applications. Written on top of Flask, Plotly.js, and React.js, Dash is ideal for building data visualization apps with highly custom user interfaces in pure Python. It's particularly suited for anyone who works with data in Python. Dash apps are rendered in the web browser. You can deploy your apps to servers and then share them through URLs. Since Dash apps are viewed in the web browser, Dash is inherently cross-platform and mobile ready. Dash is an open source library, released under the permissive MIT license. Plotly develops Dash and offers a platform for managing Dash apps in an enterprise environment. What is Web Scrapping? Web scraping is a term used to describe the use of a program or algorithm to extract and process large amounts of data from the web. Running the project Step 1: Download the dataset and extract the JSON data in your project folder. Make a folder filtered_chunks and run the data_extraction.py file. This will extract data from the JSON file into equal sized chunks and then combine them into a single CSV file called balanced_reviews.csv. Step 2: Run the data_cleaning_preprocessing_and_vectorizing.py file. This will clean and filter out the data. Next the filtered data will be fed to the TF-IDF Vectorizer and then the model will be pickled in a trained_model.pkl file and the Vocabulary of the trained model will be stored as vocab.pkl. Keep these two files in a folder named model_files. Step 3: Now run the etsy_review_scrapper.py file. Adjust the range of pages and product to be scrapped as it might take a long long time to process. A small sized data is sufficient to check the accuracy of our model. The scrapped data will be stored in csv as well as db file. Step 4: Finally, run the app.py file that will start up the Dash server and we can check the working of our model either by typing or either by selecting the preloaded scrapped reviews.
GitHub Repo
https://github.com/AlwaysSany/bigquery-hackathon
AlwaysSany/bigquery-hackathon
A bigquery powered Smart Substitute Recommender that Suggest ideal product substitutes based on a deep understanding of product attributes, not just shared tags or categories.
GitHub Repo
https://github.com/yogami/agent-semantic-aligner
yogami/agent-semantic-aligner
PROBLEM: Agents fail on vocabulary gaps ("widgets" ≠ "components") PRODUCT: Translation middleware embedding messages → shared vector space → LLM clarification → relay
GitHub Repo
https://github.com/Daniblit/Ensemble-Predictive-Model-Forecasting-AMGEN-stock-price-at-year-end-31s
Daniblit/Ensemble-Predictive-Model-Forecasting-AMGEN-stock-price-at-year-end-31s
The basis of this project involves analyzing Amgen future profitability based on its current business environment and financial performance. Technical Analysis, on the other hand, includes reading the charts and using statistical figures to identify the trends in the stock market. The dataset used for this analysis was downloaded from Yahoo finance for year 2009 to 2019. There are multiple variables in the dataset – date, open, high, low, volume. Adjusted close. The columns Open and Close represent the starting and final price at which the stock is traded on a day. High and Low represent the maximum, minimum price of the share for the day. The profit or loss calculation is usually determined by the closing price of a stock for the day, I used the adjusted closing price as the target variable. I downloaded data on the inflation rate, unemployment rate, Industrial Production Index, Consumer Price Index for All Urban Consumers: All Items and Real Gross Domestic Product as independent variables, Quarterly Financial Report: U.S. Corporations: Cash Dividends Charged to Retained Earnings All Manufacturing: All Nondurable Manufacturing: Chemicals: Pharmaceuticals and Medicines Industry, Producer Price Index by Industry: Pharmaceutical Preparation Manufacturing, 30-Year Treasury Constant Maturity Rate, and Producer Price Index by Industry: Pharmaceutical and Medicine Manufacturing Index. The independent variables are economic parameters which was obtained from Federal Reserve Economic Data (FRED) website. Methodology 1. Linear Regression: The linear regression model returns an equation that determines the relationship between the independent variables and the dependent variable. I used linear regression tool in Alteryx with ARIMA tool to forecast the stock prices for the year. The algorithm was trained with the historical data to see how the variables impact on the dependent variable. The test data was used to predict the adjusted closing price for the year and predicted a stock price of $193.38. 2. Support Vector Machines (SVM): Support Vector Networks (SVN), are a popular set of supervised learning algorithms originally developed for classification (categorical target) problems and can be used for regression (numerical target) problems. SVMs are memory efficient and can address many predictor variables. This model finds the best equation of one predictor, a plane (two predictors) or a hyperplane (three or more predictors) that maximally separates the groups of records, based on a measure of distance into different groups based on the target variable. A kernel function provides the measure of distance that causes to records to be placed in the same or different groups and involves taking a function of the predictor variables to define the distance metric. I used the SVM tool in Alteryx with ARIMA tool to forecast the stock prices for the year and predicted a stock price of $189.44. 3. Spline Model: The Spline Model tool was used because it provides the multivariate adaptive regression splines (or MARS) algorithm of Friedman. This statistical learning model self-determines which subset of fields best predict a target field of interest and can capture highly nonlinear relationships and interactions between fields. I used the Spline tool in Alteryx with ARIMA tool to forecast the stock prices for the year and predicted a stock price of $201.84. The results from the models was weighted by comparing the RMSE of each model. A lower RMSE indicates that the model’s predictions were closer to the actual values. However, a simpler model with the same RMSE as a more complex model is generally better, as simpler models are less likely to be overfit. Though the Spline model had a lower RMSE, the Linear Regression model had fewer variables. Thus, we combined the 3 models with the ARIMA forecast in a model ensemble, which allows us to use the results of multiple models. The forecasted stock price is $197.99 with 1.5% increase for 31st December 2019. Apart from economic parameters, stock price is affected by the news about the company and other factors like demonetization or merger/demerger of the companies. There are certain intangible factors which can often be impossible to predict beforehand hence the model predicts that the stock price of Amgen will continue to rise except there is a drastic downturn of the company.
GitHub Repo
https://github.com/JuliaInv/ParSpMatVec.jl
JuliaInv/ParSpMatVec.jl
Shared-memory implementation of parallel sparse matrix vector product in Julia
GitHub Repo
https://github.com/sewakshekokar/MPC-for-Privacy-Preserving-Recommendation-Systems
sewakshekokar/MPC-for-Privacy-Preserving-Recommendation-Systems
This project implements a privacy-preserving user-profile update protocol for recommendation systems using Multi-Party Computation (MPC). User and item vectors are secret-shared among parties, and secure inner product computation with Beaver triples is used to update user profiles without revealing sensitive data.
GitHub Repo
https://github.com/charleswang3/Spark98_SMVP
charleswang3/Spark98_SMVP
An optimization of Spark98's shared memory lock-based implementation of sparse matrix vector product (SMVP) using a scheduling approach to partition the sparse matrix array, removing the need for locks and allowing better write-locality at expense of read-locality and pre-processing the matrix. Authors: George Hatzis-Schoch, Charles Wang
GitHub Repo
https://github.com/Mog9/Fused-KV-Cache
Mog9/Fused-KV-Cache
Fused KV cache attention for single-token decode in one CUDA kernel using CuPy RawKernel. One query attending over the full KV cache, dot products, softmax, and weighted V sum computed entirely in shared memory with no score vector written to global memory. 8.5x faster than CuPy at short cache lengths, 2.5x at T_cache=1024.
GitHub Repo
https://github.com/kostyfisik/OMP-AVX-intrinsics-dotprod