Pinned Repositories
amazon-order-invoice-checker
A colab notebooks to integrate and lookup amazon vendor central PO/invoice and Quickbooks customer data
Audio-Recognition
This notebook tries to preprocess the .wav files and by generating their spectrogram, we can turn the problem into a image classification problem.
Autoencoder_Based_Feature_Extraction
Deep learning project on signal processing. This research is on human motion monitoring data from wearable sensor. Building a convolutional Autoencoder to decode the input signal. The encoder output can be used as compressed representations to determine the correctness of execution.
Competitor_Analysis
This app integrates e-bike’s data from different retail online stores and amazon.com, and provide interactive competitor analysis on price recommendations and feature comparisons for dynamic pricing and future product developments.
Keras-rl_DQN
Solve OpenAI GYM problem
miniTimeSeries
Create a multi-output machine learning dataframe and apply LSTM/Bidirectional LSTM with Tensorflow early stopping/model Checkpoint callbacks to predict the temperature for next several days
QB_item_quick_report
Use transactions in Quickbooks item quick report for favorable supply planning, including sales projection from previous year sales grouped by customers, Croston's method intermittent daily demand forecasting, and ARIMA forecasting on converted monthly sales. Comparing with all transactions, these analysis will focus on mainly domestic transactions for benefits on inventory planning at Phoenix location.
Recommendation_system_MF_Deep_Learning_modeling
This project is trying implement recommendation system with Keras API by collaborative filtering methods. The first model is a simple matrix factorization, which the ranking from user i to product j can be expressed as ui dot pj where elements u and p belong to decomposed user and product matricies.
Sales-Prediction---Holt-Winters-Model
Tuning Trend/ Seasonality/ Error level from Exponential Smoothing model to make futrure forcast
WordSeqenceDecoding
This notebooks, we train a seq2seq decoder model with teacher forcing. Then use the trained layers from the decoder to generate a sentence.
kaispace30098's Repositories
kaispace30098/QB_item_quick_report
Use transactions in Quickbooks item quick report for favorable supply planning, including sales projection from previous year sales grouped by customers, Croston's method intermittent daily demand forecasting, and ARIMA forecasting on converted monthly sales. Comparing with all transactions, these analysis will focus on mainly domestic transactions for benefits on inventory planning at Phoenix location.
kaispace30098/Autoencoder_Based_Feature_Extraction
Deep learning project on signal processing. This research is on human motion monitoring data from wearable sensor. Building a convolutional Autoencoder to decode the input signal. The encoder output can be used as compressed representations to determine the correctness of execution.
kaispace30098/Competitor_Analysis
This app integrates e-bike’s data from different retail online stores and amazon.com, and provide interactive competitor analysis on price recommendations and feature comparisons for dynamic pricing and future product developments.
kaispace30098/miniTimeSeries
Create a multi-output machine learning dataframe and apply LSTM/Bidirectional LSTM with Tensorflow early stopping/model Checkpoint callbacks to predict the temperature for next several days
kaispace30098/Recommendation_system_MF_Deep_Learning_modeling
This project is trying implement recommendation system with Keras API by collaborative filtering methods. The first model is a simple matrix factorization, which the ranking from user i to product j can be expressed as ui dot pj where elements u and p belong to decomposed user and product matricies.
kaispace30098/Sales-Prediction---Holt-Winters-Model
Tuning Trend/ Seasonality/ Error level from Exponential Smoothing model to make futrure forcast
kaispace30098/amazon-order-invoice-checker
A colab notebooks to integrate and lookup amazon vendor central PO/invoice and Quickbooks customer data
kaispace30098/Audio-Recognition
This notebook tries to preprocess the .wav files and by generating their spectrogram, we can turn the problem into a image classification problem.
kaispace30098/Keras-rl_DQN
Solve OpenAI GYM problem
kaispace30098/WordSeqenceDecoding
This notebooks, we train a seq2seq decoder model with teacher forcing. Then use the trained layers from the decoder to generate a sentence.
kaispace30098/Auto-ARIMA-on-Sales
automatically apply the optimal order for an ARIMA model on product sales
kaispace30098/CustomerService_QC_report
Using SQL-like functions to summerize defective products/ types, customer care agent breakdown, and freashdesk type breakdown
kaispace30098/data-mapping-woot-and-shipstation
This is an interactive notebook for transforming data to feed into both of each platform bidirectionally.
kaispace30098/Facebook_Prophet_modeling_on_Sales
In this project, the researcher try to explore the Facebook's Prophet model.Not like general autoregressive model, the y(t) is related by t itself.
kaispace30098/git_demo
gitdemo
kaispace30098/Inventory_planning_amazonVC_breakdown
This notebook breaks down Amazon Brand Analysis into per-product inventory, Open purchase order, and forecasts with customized summaries and product details to aid inventory planning.
kaispace30098/New-PO-serial-number-generator
Generate Serial number for each product in new Purchase order
kaispace30098/nlp_transfer_learning_classification
Train a model with pretrained layer from tensorflow hub (universal-sentence-encoder) for sentiment analysis
kaispace30098/Polars_reference
a quick data analysis reference by using polars dataframe instead of pandas on blending sheets and summerize.
kaispace30098/Product-Daily-Keywords
Generate a word cloud for a product from daily relatedd tweets
kaispace30098/Sentiment_analysis_on_amazon_review
Preprocess the 500K amazon reviews from raw texts into squences and fit a LSTM model with embedding layer, to determine a new review, tweet, or any product related message positive, negative.
kaispace30098/SKU_mapper
The VB script is to help to unite same products from different channels for summary and further analysis
kaispace30098/SparkRDD_wordcount
Explore RDD structures
kaispace30098/supplier_info_query
Create a Database by SQLite and run queries in SQL in assist to inventory planning
kaispace30098/Tensorflow_Object_Detection
Disclaimer: This notebook is edited from Lazy Programmer, the instructor of Deep Learning: Advanced Computer Vision for learning and experimental use only.
kaispace30098/Transfer_learning_img_classification
CIFAR-10 Image Classification.