Deep learning-based generative art is being researched. As usual, self-learning is better. Some models, like OpenAI's DALL-E 2, require registration and can only be used online, but others can be used locally, which is usually more enjoyable for curious users. I'll demonstrate the Stable Diffusion model's operation on a standard PC.

Let’s get started.

What It Does

Stable Diffusion uses numerous components:

• A generative model trained to produce images is called a diffusion model. The model is incrementally improving the starting data, which is only random noise. The model has an image, and while it is being trained, the reversed process is being used to add noise to the image. Being able to reverse this procedure and create images from noise is where the true magic is (more details and samples can be found in the paper).

• An internal compressed representation of a latent diffusion model, which may be altered to produce the desired images, is used (more details can be found in the paper). The capacity to fine-tune the generation process is essential because producing pictures at random is not very attractive (as we can see, for instance, in Generative Adversarial Networks).

• A neural network model called CLIP (Contrastive Language-Image Pre-training) is used to translate natural language prompts into vector representations. This model, which was trained on 400,000,000 image-text pairs, enables the transformation of a text prompt into a latent space for the diffusion model in the scenario of stable diffusion (more details in that paper).

This figure shows all data flow:

The weights file size for Stable Diffusion model v1 is 4 GB and v2 is 5 GB, making the model quite huge. The v1 model was trained on 256x256 and 512x512 LAION-5B pictures on a 4,000 GPU cluster using over 150.000 NVIDIA A100 GPU hours. The open-source pre-trained model is helpful for us. And we will.

Install

Before utilizing the Python sources for Stable Diffusion v1 on GitHub, we must install Miniconda (assuming Git and Python are already installed):

wget https://repo.anaconda.com/miniconda/Miniconda3-py39_4.12.0-Linux-x86_64.sh
chmod +x Miniconda3-py39_4.12.0-Linux-x86_64.sh
./Miniconda3-py39_4.12.0-Linux-x86_64.sh
conda update -n base -c defaults conda

Install the source and prepare the environment:

git clone https://github.com/CompVis/stable-diffusion
cd stable-diffusion
conda env create -f environment.yaml
conda activate ldm
pip3 install transformers --upgrade

Download the pre-trained model weights next. HiggingFace has the newest checkpoint sd-v14.ckpt (a download is free but registration is required). Put the file in the project folder and have fun:

python3 scripts/txt2img.py --prompt "hello world" --plms --ckpt sd-v1-4.ckpt --skip_grid --n_samples 1

Almost. The installation is complete for happy users of current GPUs with 12 GB or more VRAM. RuntimeError: CUDA out of memory will occur otherwise. Two solutions exist.

Running the optimized version

Try optimizing first. After cloning the repository and enabling the environment (as previously), we can run the command:

python3 optimizedSD/optimized_txt2img.py --prompt "hello world" --ckpt sd-v1-4.ckpt --skip_grid --n_samples 1

Stable Diffusion worked on my visual card with 8 GB RAM (alas, I did not behave well enough to get NVIDIA A100 for Christmas, so 8 GB GPU is the maximum I have;).

Running Stable Diffusion without GPU

If the GPU does not have enough RAM or is not CUDA-compatible, running the code on a CPU will be 20x slower but better than nothing. This unauthorized CPU-only branch from GitHub is easiest to obtain. We may easily edit the source code to use the latest version. It's strange that a pull request for that was made six months ago and still hasn't been approved, as the changes are simple. Readers can finish in 5 minutes:

• Replace if attr.device!= torch.device(cuda) with if attr.device!= torch.device(cuda) and torch.cuda.is available at line 20 of ldm/models/diffusion/ddim.py ().

• Replace if attr.device!= torch.device(cuda) with if attr.device!= torch.device(cuda) and torch.cuda.is available in line 20 of ldm/models/diffusion/plms.py ().

• Replace device=cuda in lines 38, 55, 83, and 142 of ldm/modules/encoders/modules.py with device=cuda if torch.cuda.is available(), otherwise cpu.

• Replace model.cuda() in scripts/txt2img.py line 28 and scripts/img2img.py line 43 with if torch.cuda.is available(): model.cuda ().

Run the script again.

Testing

Test the model. Text-to-image is the first choice. Test the command line example again:

python3 scripts/txt2img.py --prompt "hello world" --plms --ckpt sd-v1-4.ckpt --skip_grid --n_samples 1

The slow generation takes 10 seconds on a GPU and 10 minutes on a CPU. Final image:

Hello world is dull and abstract. Try a brush-wielding hamster. Why? Because we can, and it's not as insane as Napoleon's cat. Another image:

Generating an image from a text prompt and another image is interesting. I made this picture in two minutes using the image editor (sorry, drawing wasn't my strong suit):

I can create an image from this drawing:

python3 scripts/img2img.py --prompt "A bird is sitting on a tree branch" --ckpt sd-v1-4.ckpt --init-img bird.png --strength 0.8

It was far better than my initial drawing:

I hope readers understand and experiment.

Stable Diffusion UI

Developers love the command line, but regular users may struggle. Stable Diffusion UI projects simplify image generation and installation. Simple usage:

• Unpack the ZIP after downloading it from https://github.com/cmdr2/stable-diffusion-ui/releases. Linux and Windows are compatible with Stable Diffusion UI (sorry for Mac users, but those machines are not well-suitable for heavy machine learning tasks anyway;).

• Start the script.

Done. The web browser UI makes configuring various Stable Diffusion features (upscaling, filtering, etc.) easy:

V2.1 of Stable Diffusion

I noticed the notification about releasing version 2.1 while writing this essay, and it was intriguing to test it. First, compare version 2 to version 1:

• alternative text encoding. The Contrastive LanguageImage Pre-training (CLIP) deep learning model, which was trained on a significant number of text-image pairs, is used in Stable Diffusion 1. The open-source CLIP implementation used in Stable Diffusion 2 is called OpenCLIP. It is difficult to determine whether there have been any technical advancements or if legal concerns were the main focus. However, because the training datasets for the two text encoders were different, the output results from V1 and V2 will differ for the identical text prompts.

• a new depth model that may be used to the output of image-to-image generation.

• a revolutionary upscaling technique that can quadruple the resolution of an image.

• Generally higher resolution Stable Diffusion 2 has the ability to produce both 512x512 and 768x768 pictures.

The Hugging Face website offers a free online demo of Stable Diffusion 2.1 for code testing. The process is the same as for version 1.4. Download a fresh version and activate the environment:

conda deactivate  
conda env remove -n ldm  # Use this if version 1 was previously installed
git clone https://github.com/Stability-AI/stablediffusion
cd stablediffusion
conda env create -f environment.yaml
conda activate ldm

Hugging Face offers a new weights ckpt file.

The Out of memory error prevented me from running this version on my 8 GB GPU. Version 2.1 fails on CPUs with the slow conv2d cpu not implemented for Half error (according to this GitHub issue, the CPU support for this algorithm and data type will not be added). The model can be modified from half to full precision (float16 instead of float32), however it doesn't make sense since v1 runs up to 10 minutes on the CPU and v2.1 should be much slower. The online demo results are visible. The same hamster painting with a brush prompt yielded this result:

It looks different from v1, but it functions and has a higher resolution.

The superresolution.py script can run the 4x Stable Diffusion upscaler locally (the x4-upscaler-ema.ckpt weights file should be in the same folder):

python3 scripts/gradio/superresolution.py configs/stable-diffusion/x4-upscaling.yaml x4-upscaler-ema.ckpt

This code allows the web browser UI to select the image to upscale:

The copy-paste strategy may explain why the upscaler needs a text prompt (and the Hugging Face code snippet does not have any text input as well). I got a GPU out of memory error again, although CUDA can be disabled like v1. However, processing an image for more than two hours is unlikely:

Stable Diffusion Limitations

When we use the model, it's fun to see what it can and can't do. Generative models produce abstract visuals but not photorealistic ones. This fundamentally limits The generative neural network was trained on text and image pairs, but humans have a lot of background knowledge about the world. The neural network model knows nothing. If someone asks me to draw a Chinese text, I can draw something that looks like Chinese but is actually gibberish because I never learnt it. Generative AI does too! Humans can learn new languages, but the Stable Diffusion AI model includes only language and image decoder brain components. For instance, the Stable Diffusion model will pull NO WAR banner-bearers like this:

V1:

V2.1:

The shot shows text, although the model never learned to read or write. The model's string tokenizer automatically converts letters to lowercase before generating the image, so typing NO WAR banner or no war banner is the same.

I can also ask the model to draw a gorgeous woman:

V1:

V2.1:

The first image is gorgeous but physically incorrect. A second one is better, although it has an Uncanny valley feel. BTW, v2 has a lifehack to add a negative prompt and define what we don't want on the image. Readers might try adding horrible anatomy to the gorgeous woman request.

If we ask for a cartoon attractive woman, the results are nice, but accuracy doesn't matter:

V1:

V2.1:

Another example: I ordered a model to sketch a mouse, which looks beautiful but has too many legs, ears, and fingers:

V1:

V2.1: improved but not perfect.

V1 produces a fun cartoon flying mouse if I want something more abstract:

I tried multiple times with V2.1 but only received this:

The image is OK, but the first version is closer to the request.

Stable Diffusion struggles to draw letters, fingers, etc. However, abstract images yield interesting outcomes. A rural landscape with a modern metropolis in the background turned out well:

V1:

V2.1:

Generative models help make paintings too (at least, abstract ones). I searched Google Image Search for modern art painting to see works by real artists, and this was the first image:

I typed "abstract oil painting of people dancing" and got this:

V1:

V2.1:

It's a different style, but I don't think the AI-generated graphics are worse than the human-drawn ones.

The AI model cannot think like humans. It thinks nothing. A stable diffusion model is a billion-parameter matrix trained on millions of text-image pairs. I input "robot is creating a picture with a pen" to create an image for this post. Humans understand requests immediately. I tried Stable Diffusion multiple times and got this:

This great artwork has a pen, robot, and sketch, however it was not asked. Maybe it was because the tokenizer deleted is and a words from a statement, but I tried other requests such robot painting picture with pen without success. It's harder to prompt a model than a person.

I hope Stable Diffusion's general effects are evident. Despite its limitations, it can produce beautiful photographs in some settings. Readers who want to use Stable Diffusion results should be warned. Source code examination demonstrates that Stable Diffusion images feature a concealed watermark (text StableDiffusionV1 and SDV2) encoded using the invisible-watermark Python package. It's not a secret, because the official Stable Diffusion repository's test watermark.py file contains a decoding snippet. The put watermark line in the txt2img.py source code can be removed if desired. I didn't discover this watermark on photographs made by the online Hugging Face demo. Maybe I did something incorrectly (but maybe they are just not using the txt2img script on their backend at all).

Conclusion

The Stable Diffusion model was fascinating. As I mentioned before, trying something yourself is always better than taking someone else's word, so I encourage readers to do the same (including this article as well;).

Is Generative AI a game-changer? My humble experience tells me:

• I think that place has a lot of potential. For designers and artists, generative AI can be a truly useful and innovative tool. Unfortunately, it can also pose a threat to some of them since if users can enter a text field to obtain a picture or a website logo in a matter of clicks, why would they pay more to a different party? Is it possible right now? unquestionably not yet. Images still have a very poor quality and are erroneous in minute details. And after viewing the image of the stunning woman above, models and fashion photographers may also unwind because it is highly unlikely that AI will replace them in the upcoming years.

• Today, generative AI is still in its infancy. Even 768x768 images are considered to be of a high resolution when using neural networks, which are computationally highly expensive. There isn't an AI model that can generate high-resolution photographs natively without upscaling or other methods, at least not as of the time this article was written, but it will happen eventually.

• It is still a challenge to accurately represent knowledge in neural networks (information like how many legs a cat has or the year Napoleon was born). Consequently, AI models struggle to create photorealistic photos, at least where little details are important (on the other side, when I searched Google for modern art paintings, the results are often even worse;).

• When compared to the carefully chosen images from official web pages or YouTube reviews, the average output quality of a Stable Diffusion generation process is actually less attractive because to its high degree of randomness. When using the same technique on their own, consumers will theoretically only view those images as 1% of the results.

Anyway, it's exciting to witness this area's advancement, especially because the project is open source. Google's Imagen and DALL-E 2 can also produce remarkable findings. It will be interesting to see how they progress.

This method scrapes websites with ChatGPT (demo with Amazon and Twitter)

In a recent article, I demonstrated how to scrape websites using ChatGPT prompts like scrape website X using Python.

But that doesn’t always work.

After scraping dozens of websites with ChatGPT, I realized that simple prompts rarely work for web scraping.

Using ChatGPT and basic HTML, we can scrape any website.

First things first, use ChatGPT's advanced version (Playground)

ChatGPT Playground's enhanced version is needed to scrape websites quickly. It generates code faster and has less constraints.

Here’s how it looks.

The classic ChatGPT display just allows you to type a prompt. Playground is more customizable and generates code faster than the basic version.

No more delays or restrictions.

In this tutorial, we'll write prompts underneath Playground.

How to Use ChatGPT to Scrape Any Website

To show you how to utilize ChatGPT to scrape any website, we'll use subslikescript, which lists movies.

Later in this post, I'll show you how to scrape Amazon and Twitter, but let's start easy.

If we try a basic prompt like “scrape the movie titles on this website: https://subslikescript.com/movies” it won’t scrape anything. Here’s when we need some HTML knowledge to build the right prompt for ChatGPT.Let's scrape the above movie titles. First, check the webpage. Right-click any element and choose Inspect.

Then see below.

We identify the element to scrape (those in the red box). The data elements are ul, a, and scripts-list.

Here's the prompt for movie titles.

Scrape this website: https://subslikescript.com/movies with Python and Beautiful Soup. Locate the element with tag “ul” and class “scripts-list”. Scrape all the “a” elements inside. Get the text attribute and print it.

Code generated:

import requests
from bs4 import BeautifulSoup

page = requests.get('https://subslikescript.com/movies/')

soup = BeautifulSoup(page.content, 'html.parser')

scripts_list = soup.find(class_="scripts-list")

all_a_elements = scripts_list.find_all('a')

for element in all_a_elements:
    print(element.get_text())

It extracts movie titles successfully.

Let's scrape Amazon and Twitter.

ChatGPT's Amazon scraping

Consider scraping Amazon for self-help books. First, copy the Amazon link for self-help books.

Here’s the link I got. Location-dependent connection. Use my link to replicate my results.

Now we'll check book titles. Here's our element.

If we want to extract the book titles, we need to use the tag name span, class attribute name and a-size-base-plus a-color-base a-text-normalattribute value.

This time I'll use Selenium. I'll add Selenium-specific commands like wait 5 seconds and generate an XPath.

Scrape this website https://www.amazon.com/s?k=self+help+books&sprefix=self+help+%2Caps%2C158&ref=nb_sb_ss_ts-doa-p_2_10 with Python and Selenium.

Wait 5 seconds and locate all the elements with the following xpath: “span” tag, “class” attribute name, and “a-size-base-plus a-color-base a-text-normal” attribute value. Get the text attribute and print them.

Code generated: (I only had to manually add the path where my chromedriver is located).

from selenium import webdriver
from selenium.webdriver.common.by import By
from time import sleep

#initialize webdriver
driver = webdriver.Chrome('<add path of your chromedriver>')

#navigate to the website
driver.get("https://www.amazon.com/s?k=self+help+books&sprefix=self+help+%2Caps%2C158&ref=nb_sb_ss_ts-doa-p_2_10")

#wait 5 seconds to let the page load
sleep(5)

#locate all the elements with the following xpath
elements = driver.find_elements(By.XPATH, '//span[@class="a-size-base-plus a-color-base a-text-normal"]')

#get the text attribute of each element and print it
for element in elements:
    print(element.text)

#close the webdriver
driver.close()

It pulls Amazon book titles.

Utilizing ChatGPT to scrape Twitter

Say you wish to scrape ChatGPT tweets. Search Twitter for ChatGPT and copy the URL.

Here’s the link I got. We must check every tweet. Here's our element.

To extract a tweet, use the div tag and lang attribute.

Again, Selenium.

Scrape this website: https://twitter.com/search?q=chatgpt&src=typed_query using Python, Selenium and chromedriver.

Maximize the window, wait 15 seconds and locate all the elements that have the following XPath: “div” tag, attribute name “lang”. Print the text inside these elements.

Code generated: (again, I had to add the path where my chromedriver is located)

from selenium import webdriver
import time

driver = webdriver.Chrome("/Users/frankandrade/Downloads/chromedriver")
driver.maximize_window()
driver.get("https://twitter.com/search?q=chatgpt&src=typed_query")
time.sleep(15)

elements = driver.find_elements_by_xpath("//div[@lang]")
for element in elements:
    print(element.text)

driver.quit()

You'll get the first 2 or 3 tweets from a search. To scrape additional tweets, click X times.

Congratulations! You scraped websites without coding by using ChatGPT.

It's cheaper, faster charging, longer lasting, safer, and better for the environment.

Batteries are the future. Next-gen and planet-saving technology, including solar power and EVs, require batteries. As these smart technologies become more popular, we find that our batteries can't keep up. Lithium-ion batteries are expensive, slow to charge, big, fast to decay, flammable, and not environmentally friendly. MIT just created a new battery that eliminates all of these problems.  So, is this the battery of the future? Or is there a catch?

When I say entirely new, I mean it. This battery employs no currently available materials. Its electrodes are constructed of aluminium and pure sulfur instead of lithium-complicated ion's metals and graphite. Its electrolyte is formed of molten chloro-aluminate salts, not an organic solution with lithium salts like lithium-ion batteries.

How does this change in materials help?

Aluminum, sulfur, and chloro-aluminate salts are abundant, easy to acquire, and cheap. This battery might be six times cheaper than a lithium-ion battery and use less hazardous mining. The world and our wallets will benefit.

But don’t go thinking this means it lacks performance.

This battery charged in under a minute in tests. At 25 degrees Celsius, the battery will charge 25 times slower than at 110 degrees Celsius. This is because the salt, which has a very low melting point, is in an ideal state at 110 degrees and can carry a charge incredibly quickly. Unlike lithium-ion, this battery self-heats when charging and discharging, therefore no external heating is needed.

Anyone who's seen a lithium-ion battery burst might be surprised. Unlike lithium-ion batteries, none of the components in this new battery can catch fire. Thus, high-temperature charging and discharging speeds pose no concern.

These batteries are long-lasting. Lithium-ion batteries don't last long, as any iPhone owner can attest. During charging, metal forms a dendrite on the electrode. This metal spike will keep growing until it reaches the other end of the battery, short-circuiting it. This is why phone batteries only last a few years and why electric car range decreases over time. This new battery's molten salt slows deposition, extending its life. This helps the environment and our wallets.

These batteries are also energy dense. Some lithium-ion batteries have 270 Wh/kg energy density (volume and mass). Aluminum-sulfur batteries could have 1392 Wh/kg, according to calculations. They'd be 5x more energy dense. Tesla's Model 3 battery would weigh 96 kg instead of 480 kg if this battery were used. This would improve the car's efficiency and handling.

These calculations were for batteries without molten salt electrolyte. Because they don't reflect the exact battery chemistry, they aren't a surefire prediction.

This battery seems great. It will take years, maybe decades, before it reaches the market and makes a difference. Right?

Nope. The project's scientists founded Avanti to develop and market this technology.

So we'll soon be driving cheap, durable, eco-friendly, lightweight, and ultra-safe EVs? Nope.

This battery must be kept hot to keep the salt molten; otherwise, it won't work and will expand and contract, causing damage. This issue could be solved by packs that can rapidly pre-heat, but that project is far off.

Rapid and constant charge-discharge cycles make these batteries ideal for solar farms, homes, and EV charging stations. The battery is constantly being charged or discharged, allowing it to self-heat and maintain an ideal temperature.

These batteries aren't as sexy as those making EVs faster, more efficient, and cheaper. Grid batteries are crucial to our net-zero transition because they allow us to use more low-carbon energy. As we move away from fossil fuels, we'll need millions of these batteries, so the fact that they're cheap, safe, long-lasting, and environmentally friendly will be huge. Who knows, maybe EVs will use this technology one day. MIT has created another world-changing technology.

Python Heatmap Technical Indicator

Heatmaps provide an instant overview. They can be used with correlations or to predict reactions or confirm the trend in trading. This article covers RSI heatmap creation.

The Market System

Market regime:

• Bullish trend: The market tends to make higher highs, which indicates that the overall trend is upward.

• Sideways: The market tends to fluctuate while staying within predetermined zones.

• Bearish trend: The market has the propensity to make lower lows, indicating that the overall trend is downward.

Most tools detect the trend, but we cannot predict the next state. The best way to solve this problem is to assume the current state will continue and trade any reactions, preferably in the trend.

If the EURUSD is above its moving average and making higher highs, a trend-following strategy would be to wait for dips before buying and assuming the bullish trend will continue.

Indicator of Relative Strength

J. Welles Wilder Jr. introduced the RSI, a popular and versatile technical indicator. Used as a contrarian indicator to exploit extreme reactions. Calculating the default RSI usually involves these steps:

• Determine the difference between the closing prices from the prior ones.

• Distinguish between the positive and negative net changes.

• Create a smoothed moving average for both the absolute values of the positive net changes and the negative net changes.

• Take the difference between the smoothed positive and negative changes. The Relative Strength RS will be the name we use to describe this calculation.

• To obtain the RSI, use the normalization formula shown below for each time step.

The 13-period RSI and black GBPUSD hourly values are shown above. RSI bounces near 25 and pauses around 75. Python requires a four-column OHLC array for RSI coding.

import numpy as np
def add_column(data, times):
    
    for i in range(1, times + 1):
    
        new = np.zeros((len(data), 1), dtype = float)
        
        data = np.append(data, new, axis = 1)
    return data
def delete_column(data, index, times):
    
    for i in range(1, times + 1):
    
        data = np.delete(data, index, axis = 1)
    return data
def delete_row(data, number):
    
    data = data[number:, ]
    
    return data
def ma(data, lookback, close, position): 
    
    data = add_column(data, 1)
    
    for i in range(len(data)):
           
            try:
                
                data[i, position] = (data[i - lookback + 1:i + 1, close].mean())
            
            except IndexError:
                
                pass
            
    data = delete_row(data, lookback)
    
    return data
def smoothed_ma(data, alpha, lookback, close, position):
    
    lookback = (2 * lookback) - 1
    
    alpha = alpha / (lookback + 1.0)
    
    beta  = 1 - alpha
    
    data = ma(data, lookback, close, position)
    data[lookback + 1, position] = (data[lookback + 1, close] * alpha) + (data[lookback, position] * beta)
    for i in range(lookback + 2, len(data)):
        
            try:
                
                data[i, position] = (data[i, close] * alpha) + (data[i - 1, position] * beta)
        
            except IndexError:
                
                pass
            
    return data
def rsi(data, lookback, close, position):
    
    data = add_column(data, 5)
    
    for i in range(len(data)):
        
        data[i, position] = data[i, close] - data[i - 1, close]
     
    for i in range(len(data)):
        
        if data[i, position] > 0:
            
            data[i, position + 1] = data[i, position]
            
        elif data[i, position] < 0:
            
            data[i, position + 2] = abs(data[i, position])
            
    data = smoothed_ma(data, 2, lookback, position + 1, position + 3)
    data = smoothed_ma(data, 2, lookback, position + 2, position + 4)
    data[:, position + 5] = data[:, position + 3] / data[:, position + 4]
    
    data[:, position + 6] = (100 - (100 / (1 + data[:, position + 5])))
    data = delete_column(data, position, 6)
    data = delete_row(data, lookback)
    return data

Make sure to focus on the concepts and not the code. You can find the codes of most of my strategies in my books. The most important thing is to comprehend the techniques and strategies.

My weekly market sentiment report uses complex and simple models to understand the current positioning and predict the future direction of several major markets. Check out the report here:

Using the Heatmap to Find the Trend

RSI trend detection is easy but useless. Bullish and bearish regimes are in effect when the RSI is above or below 50, respectively. Tracing a vertical colored line creates the conditions below. How:

• When the RSI is higher than 50, a green vertical line is drawn.

• When the RSI is lower than 50, a red vertical line is drawn.

Zooming out yields a basic heatmap, as shown below.

Plot code:

def indicator_plot(data, second_panel, window = 250):
    fig, ax = plt.subplots(2, figsize = (10, 5))
    sample = data[-window:, ]
    for i in range(len(sample)):
        ax[0].vlines(x = i, ymin = sample[i, 2], ymax = sample[i, 1], color = 'black', linewidth = 1)  
        if sample[i, 3] > sample[i, 0]:
            ax[0].vlines(x = i, ymin = sample[i, 0], ymax = sample[i, 3], color = 'black', linewidth = 1.5)  
        if sample[i, 3] < sample[i, 0]:
            ax[0].vlines(x = i, ymin = sample[i, 3], ymax = sample[i, 0], color = 'black', linewidth = 1.5)  
        if sample[i, 3] == sample[i, 0]:
            ax[0].vlines(x = i, ymin = sample[i, 3], ymax = sample[i, 0], color = 'black', linewidth = 1.5)  
    ax[0].grid() 
    for i in range(len(sample)):
        if sample[i, second_panel] > 50:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'green', linewidth = 1.5)  
        if sample[i, second_panel] < 50:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'red', linewidth = 1.5)  
    ax[1].grid()
indicator_plot(my_data, 4, window = 500)

Call RSI on your OHLC array's fifth column. 4. Adjusting lookback parameters reduces lag and false signals. Other indicators and conditions are possible.

Another suggestion is to develop an RSI Heatmap for Extreme Conditions.

Contrarian indicator RSI. The following rules apply:

• Whenever the RSI is approaching the upper values, the color approaches red.

• The color tends toward green whenever the RSI is getting close to the lower values.

Zooming out yields a basic heatmap, as shown below.

Plot code:

import matplotlib.pyplot as plt
def indicator_plot(data, second_panel, window = 250):
    fig, ax = plt.subplots(2, figsize = (10, 5))
    sample = data[-window:, ]
    for i in range(len(sample)):
        ax[0].vlines(x = i, ymin = sample[i, 2], ymax = sample[i, 1], color = 'black', linewidth = 1)  
        if sample[i, 3] > sample[i, 0]:
            ax[0].vlines(x = i, ymin = sample[i, 0], ymax = sample[i, 3], color = 'black', linewidth = 1.5)  
        if sample[i, 3] < sample[i, 0]:
            ax[0].vlines(x = i, ymin = sample[i, 3], ymax = sample[i, 0], color = 'black', linewidth = 1.5)  
        if sample[i, 3] == sample[i, 0]:
            ax[0].vlines(x = i, ymin = sample[i, 3], ymax = sample[i, 0], color = 'black', linewidth = 1.5)  
    ax[0].grid() 
    for i in range(len(sample)):
        if sample[i, second_panel] > 90:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'red', linewidth = 1.5)  
        if sample[i, second_panel] > 80 and sample[i, second_panel] < 90:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'darkred', linewidth = 1.5)  
        if sample[i, second_panel] > 70 and sample[i, second_panel] < 80:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'maroon', linewidth = 1.5)  
        if sample[i, second_panel] > 60 and sample[i, second_panel] < 70:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'firebrick', linewidth = 1.5) 
        if sample[i, second_panel] > 50 and sample[i, second_panel] < 60:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'grey', linewidth = 1.5) 
        if sample[i, second_panel] > 40 and sample[i, second_panel] < 50:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'grey', linewidth = 1.5) 
        if sample[i, second_panel] > 30 and sample[i, second_panel] < 40:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'lightgreen', linewidth = 1.5)
        if sample[i, second_panel] > 20 and sample[i, second_panel] < 30:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'limegreen', linewidth = 1.5) 
        if sample[i, second_panel] > 10 and sample[i, second_panel] < 20:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'seagreen', linewidth = 1.5)  
        if sample[i, second_panel] > 0 and sample[i, second_panel] < 10:
            ax[1].vlines(x = i, ymin = 0, ymax = 100, color = 'green', linewidth = 1.5)
    ax[1].grid()
indicator_plot(my_data, 4, window = 500)

Dark green and red areas indicate imminent bullish and bearish reactions, respectively. RSI around 50 is grey.

Summary

To conclude, my goal is to contribute to objective technical analysis, which promotes more transparent methods and strategies that must be back-tested before implementation.

Technical analysis will lose its reputation as subjective and unscientific.

When you find a trading strategy or technique, follow these steps:

• Put emotions aside and adopt a critical mindset.

• Test it in the past under conditions and simulations taken from real life.

• Try optimizing it and performing a forward test if you find any potential.

• Transaction costs and any slippage simulation should always be included in your tests.

• Risk management and position sizing should always be considered in your tests.

After checking the above, monitor the strategy because market dynamics may change and make it unprofitable.

Perovskite solar cells will revolutionize everything.

Humanity is in a climatic Armageddon. Our widespread ecological crimes of the previous century are catching up with us, and planet-scale karma threatens everyone. We must adjust to new technologies and lifestyles to avoid this fate. Even solar power, a renewable energy source, has climate problems. A recent discovery could boost solar power's eco-friendliness and affordability. Perovskite solar cells are amazing.

Perovskite is a silicon-like semiconductor. Semiconductors are used to make computer chips, LEDs, camera sensors, and solar cells. Silicon makes sturdy and long-lasting solar cells, thus it's used in most modern solar panels.

Perovskite solar cells are far better. First, they're easy to make at room temperature, unlike silicon cells, which require long, intricate baking processes. This makes perovskite cells cheaper to make and reduces their carbon footprint. Perovskite cells are efficient. Most silicon panel solar farms are 18% efficient, meaning 18% of solar radiation energy is transformed into electricity. Perovskite cells are 25% efficient, making them 38% more efficient than silicon.

However, perovskite cells are nowhere near as durable. A normal silicon panel will lose efficiency after 20 years. The first perovskite cells were ineffective since they lasted barely minutes.

Recent research from Princeton shows that perovskite cells can endure 30 years. The cells kept their efficiency, therefore no sacrifices were made.

No electrical or chemical engineer here, thus I can't explain how they did it. But strangely, the team said longevity isn't the big deal. In the next years, perovskite panels will become longer-lasting. How do you test a panel if you only have a month or two? This breakthrough technique needs a uniform method to estimate perovskite life expectancy fast. The study's key milestone was establishing a standard procedure.

Lab-based advanced aging tests are their solution. Perovskite cells decay faster at higher temperatures, so scientists can extrapolate from that. The test heated the panel to 110 degrees and waited for its output to reduce by 20%. Their panel lasted 2,100 hours (87.5 days) before a 20% decline.

They did some math to extrapolate this data and figure out how long the panel would have lasted in different climates, and were shocked to find it would last 30 years in Princeton. This made perovskite panels as durable as silicon panels. This panel could theoretically be sold today.

This technology will soon allow these brilliant panels to be released into the wild. This technology could be commercially viable in ten, maybe five years.

Solar power will be the best once it does. Solar power is cheap and low-carbon. Perovskite is the cheapest renewable energy source if we switch to it. Solar panel manufacturing's carbon footprint will also drop.

Perovskites' impact goes beyond cost and carbon. Silicon panels require harmful mining and contain toxic elements (cadmium). Perovskite panels don't require intense mining or horrible materials, making their production and expiration more eco-friendly.

Solar power destroys habitat. Massive solar farms could reduce biodiversity and disrupt local ecology by destroying vital habitats. Perovskite cells are more efficient, so they can shrink a solar farm while maintaining energy output. This reduces land requirements, making perovskite solar power cheaper, and could reduce solar's environmental impact.

Perovskite solar power is scalable and environmentally friendly. Princeton scientists will speed up the development and rollout of this energy.

Why bother with fusion, fast reactors, SMRs, or traditional nuclear power? We're close to developing a nearly perfect environmentally friendly power source, and we have the tools and systems to do so quickly. It's also affordable, so we can adopt it quickly and let the developing world use it to grow. Even I struggle to justify spending billions on fusion when a great, cheap technology outperforms it. Perovskite's eco-credentials and cost advantages could save the world and power humanity's future.

I'd spend hours composing articles only to find out they were useless. Twitter solved the problem.

Twitter is wrinkled, say critics.

Nope. Writing is different. It won't make sense until you write there.

Twitter is resurgent. People are reading again. 15-second TikToks overloaded our senses.

After nuking my 20,000-follower Twitter account and starting again, I wrote every day for 210 days.

I'll explain.

I came across the strange world of microblogging.

Traditional web writing is filler-heavy.

On Twitter, you must be brief. I played Wordle.

Twitter Threads are the most popular writing format. Like a blog post. It reminds me of the famous broetry posts on LinkedIn a few years ago.

Threads combine tweets into an article.

• Sharp, concise sentences

• No regard for grammar

• As important as the information is how the text looks.

Twitter Threads are like Michael Angelo's David monument. He chipped away at an enormous piece of marble until a man with a big willy appeared.

That's Twitter Threads.

I tried to remove unnecessary layers from several of my Wordpress blog posts. Then I realized something.

Tweeting from scratch is easier and more entertaining. It's quicker and makes you think more concisely.

Superpower: saying much with little words. My long-form writing has improved. My article sentences resemble tweets.

You never know what will happen.

Twitter's subcultures are odd. Best-performing tweets are strange.

Unusual trend: working alone and without telling anyone. It's a rebellion against Instagram influencers who share their every moment.

Early on, random thoughts worked:

My friend’s wife is Ukrainian. Her family are trapped in the warzone. He is devastated. And here I was complaining about my broken garage door. War puts everything in perspective. Today is a day to be grateful for peace.

Documenting what's happening triggers writing. It's not about viral tweets. Helping others matters.

There are numerous anonymous users.

Twitter uses pseudonyms.

You don't matter. On sites like LinkedIn, you must use your real name. Welcome to the Cyberpunk metaverse of Twitter :)

One daily piece of writing is a powerful habit.

Habits build creator careers. Read that again.

Twitter is an easy habit to pick up. If you can't tweet in one sentence, something's wrong. Easy-peasy-japanese.

Not what I tweeted, but my constancy, made the difference.

Daily writing is challenging, especially if your supervisor is on your back. Twitter encourages writing.

Tweets evolved as the foundation of all other material.

During my experiment, I enjoyed Twitter's speed.

Tweets get immediate responses, comments, and feedback. My popular tweets become newspaper headlines. I've also written essays from tweet discussions.

Sometimes the tweet and article were clear. Twitter sometimes helped me overcome writer's block.

I used to spend hours composing big things that had little real-world use.

Twitter helped me. No guessing. Data guides my coverage and validates concepts.

Test ideas on Twitter.

It took some time for my email list to grow.

Subscribers are a writer's lifeblood.

Without them, you're broke and homeless when Mark Zuckerberg tweaks the algorithms for ad dollars. Twitter has three ways to obtain email subscribers:

1. Add a link to your bio.

Twitter allows bio links (LinkedIn now does too). My eBook's landing page is linked. I collect emails there.

2. Start an online newsletter.

Twitter bought newsletter app Revue. They promote what they own.

I just established up a Revue email newsletter. I imported them weekly into my ConvertKit email list.

3. Create Twitter threads and include a link to your email list in the final tweet.

Write Twitter Threads and link the last tweet to your email list (example below).

Initial email subscribers were modest.

Numbers are growing. Twitter provides 25% of my new email subscribers. Some days, 50 people join.

Without them, my writing career is over. I'd be back at a 9-5 job begging for time off to spend with my newborn daughter. Nope.

Collect email addresses or die trying.

As insurance against unsubscribes and Zucks, use a second email list or Discord community.

What I still need to do

Twitter's fun. I'm wiser. I need to enable auto-replies and auto-DMs (direct messages).

This adds another way to attract subscribers. I schedule tweets with Tweet Hunter.

It’s best to go slow. People assume you're an internet marketer if you spam them with click requests.

A human internet marketer is preferable to a robot. My opinion.

210 days on Twitter taught me that. I plan to use the platform until I'm a grandfather unless Elon ruins it.