Dr Crypto

Now that I am only downloading data on 5,000 cryptos daily from CoinGecko, I needed to subset my other files so that they only contained 5,000 cryptos. Here is the code, I used to manage the files. Python Code import os import glob import csv import pandas as pd print(os.getcwd()) os.listdir() path_dir = 'CGdata_s3_AugSeptOctNovDec_2022_old' new_dir = "Cryptos_5000_Data/" all_files = os.listdir(path_dir)     csv_files = list(filter(lambda f: f.endswith('.csv'), all_files)) for i in csv_files:     file_path = path_dir + "/" + i     data = pd.read_csv(file_path, nrows = 5000)     path_file = path_dir + "/" + new_dir + i     data.to_csv(path_file,  index = False )

I have been experimenting with Matplotlib's twinx() method.  I learned about the method from Datacamp's Python visualization skills course.  After each new course, I try to integrate at least 1 learning into my Crypto project.  Below is a chart with Bitcoin's and Ripple (XRP)'s prices. Bitcoin and Ripple (XRP) prices 

    Using an RNN model, I tried to predict Polygon (Matic-network)' s price from January 1, 2023 - April 16, 2023. Overall, I followed the same format as my past price predictions: 75 epochs. Here is the info: Recurrent Neural Network (LSTM) Training on 60 days of past price Predicting 1 day out Training data: June 20, 2021 - Dec 31, 2022 Training epochs: 75 Training mean square error: loss: 0.0037 Testing data: January 1, 2023 - April 16, 2023 Data source: Coingecko.com Here is the chart detailing the actual Polygon Matic-Network's price with the RNN predictions.

  Using an RNN model, I tried to predict XRP (Ripple)' s price from January 1, 2023 - April 16, 2023. Overall, I followed the same format as my past price predictions; however, in this model, I only ran 75 epochs. Here is the info: Recurrent Neural Network (LSTM) Training on 60 days of past price Predicting 1 day out Training data: June 20, 2021 - Dec 31, 2022 Training epochs: 75 Training mean square error: loss: 0.0023 (update) Testing data: January 1, 2023 - April 16, 2023 Data source: Coingecko.com Here is the chart detailing the actual XRP Ripple's price with the RNN predictions.

Bad news today! I received an error message from CoinGecko for exceeding the rate limit.  I will have to decide if I will purchase a monthly plan or if I will update my date weekly or monthly.   While I understand why CoinGecko has blocked me from downloading data, I am extremely disappointed because getting interesting data is difficult.  This project was also starting to become very interesting to me. Here is the error message I received this morning.

  Using an RNN model, I tried to predict Dogecoin's price from January 1, 2023 - April 16, 2023. Overall, I followed the same format as my past price predictions; however, in this model, I only ran 75 epochs. Here is the info: Recurrent Neural Network (LSTM) Training on 60 days of past price Predicting 1 day out Training data: June 20, 2021 - Dec 31, 2022 Training epochs: 75 Training mean square error: loss: 0.0023 Testing data: January 1, 2023 - April 16, 2023 Data source: Coingecko.com Here is the chart detailing the actual Dogecoin's price with the RNN predictions.

  Using an RNN model, I tried to predict Bitcoin's price from January 1, 2023 - April 16, 2023. Overall, I followed the same format as my past price predictions; however, in this model, I only ran 75 epochs as opposed to 100. The mean square error was higher but I don't believe this made much of a difference with the price predictions. Here is the info: Recurrent Neural Network (LSTM) Training on 60 days of past price Predicting 1 day out Training data: June 20, 2021 - Dec 31, 2022 Training epochs: 75 Training mean square error: loss: 0.0027 Testing data: January 1, 2023 - April 16, 2023 Data source: Coingecko.com Here is the chart detailing the actual Bitcon's price with the RNN predictions.

Using an RNN model, I tried to predict Solana's price from January 1, 2023 - February 28, 2023. Overall, I followed the same format as my past price predictions; however, in this model, I only ran 75 epochs as opposed to 100. The mean square error was higher but I don't believe this made much of a difference with the price predictions. Here is the info: Recurrent Neural Network (LSTM) Training on 60 days of past price Predicting 1 day out Training data: June 20, 2021 - Dec 31, 2022 Training epochs: 75 Training mean square error: loss: 0.0030 Testing data: January 1, 2023 - February 28, 2023 Data source: Coingecko.com Here is the chart detailing the actual Cardano price with the RNN predictions. (Note: The chart is in French as I am taking a deep learning course in French. I will be producing more charts so future charts will be in English)

Using an RNN model, I tried to predict Cardano's price from January 1, 2023 - February 28, 2023. Here is the info: Recurrent Neural Network (LSTM) Training on 60 days of past price Predicting 1 day out Training data: June 20, 2021 - Dec 31, 2022 Training epochs : 100 Training mean square error: loss: 0.0014 Testing data: January 1, 2023 - February 28, 2023 Data source: Coingecko.com Here is the chart detailing the actual Cardano price with the RNN predictions. (Note: The chart is in French as I am taking a deep learning course in French. I will be producing more charts so future charts will be in English)

Using an RNN model, I tried to predict Ethereum's price from January 1, 2023 - February 28, 2023. Here is the info: Recurrent Neural Network (LSTM) Training on 60 days of past price Predicting 1 day out Training data: June 20, 2021 - Dec 31, 2022 Training epochs : 100 Training mean square error: loss: 0.0027 Testing data: January 1, 2023 - February 28, 2023 Data source: Coingecko.com Here is the chart detailing the actual Ethereum price with the RNN predictions. (Note: The chart is in French as I am taking a deep learning course in French. I will be producing more charts so future charts will be in English)

I have been experimenting and learning about Recurrent Neural Networks (RNNs).  In the course that I took, I trained a model to predict Google's stock price.  Based on the success of the model, I decided to use the same program to try to predict Bitcoin's price from January 1, 2023 - February 28, 2023. Here is the info: Recurrent Neural Network (LSTM) Training on 60 days of past price Predicting 1 day out Training data: June 20, 2021 - Dec 31, 2022 Training epochs : 100 Training mean square error: loss: 0.0024 Testing data: January 1, 2023 - February 28, 2023 Data source: Coingecko.com Here is the chart detailing the actual Bitcoin price with the RNN predictions. (Note: The chart is in French as I am taking a deep learning course in French. I will be producing more charts so future charts will be in English)

  Many people think that Solana is dead because of the numerous network outages.  Is Solana dead?  Let's ask ChatCPT.... Q : Why does Solana still keep having problems with its network? ChatGPT: While Solana is designed to be a high-performance and scalable blockchain platform, it has experienced several network issues in the past. Some of the reasons for these problems include: 1) Network congestion: As more applications and users have joined the Solana network, the network has become congested, leading to delays and slower transaction processing times. This has resulted in higher fees and increased the risk of network congestion-related issues. 2) Centralization of network validators: The Solana network currently relies on a limited number of validators, which are responsible for validating transactions and maintaining the integrity of the blockchain. This centralization has raised concerns about the security and decentralization of the network, particularly if the...

  Here is another discussion I had with ChatGPT4 regarding cryptocurrencies: Q: S hould I invest in Ethereum, XRP, or Bitcoin? ChatGPT: As an AI language model, I cannot provide personalized investment advice or recommend specific cryptocurrencies to invest in. However, I can provide some general information about each cryptocurrency to help you make an informed decision. Bitcoin is the oldest and most well-known cryptocurrency, and it is often viewed as a store of value or a potential hedge against inflation. Bitcoin's value is derived from its scarcity and the demand for it from users and investors. Ethereum is a blockchain platform that allows developers to build decentralized applications (dapps) and smart contracts. The native cryptocurrency of the Ethereum blockchain is Ether (ETH), and it is used to pay transaction fees and incentivize miners on the network. Ethereum is also known for its ability to support a wide range of decentralized finance (DeFi) applications. XRP ...

  Today, I decided to see if I could use ChatGPT with my crypto bog.  Here is a test run... Q1: What is Bitcoin? ChatGPT: Bitcoin is a decentralized digital currency that allows for peer-to-peer transactions without the need for a central authority such as a bank or government. It was created in 2009 by an unknown person or group using the pseudonym "Satoshi Nakamoto." Bitcoin operates on a decentralized ledger called the blockchain, which records all transactions and ensures their validity. Transactions are verified by network nodes through cryptography and recorded in a public distributed ledger called a blockchain. Bitcoin is unique because it has a limited supply of 21 million bitcoins that will ever be created, and it is deflationary in nature, meaning that as time goes on, fewer and fewer bitcoins will be produced. It has been the subject of controversy and debate, with some people seeing it as a revolutionary new technology that could change the world of finance, w...