Mohammed A. AL-Maamari ModMaamari

## from_label_studio_to_dataframe.py
def from_label_studio_to_dataframe( LABEL_STUDIO_URL="",
                                    API_KEY=""):
    '''
    Goals:
        - Load the labeled data from Label Studio
            (or from a raw_data dictionary saved locally as a pickle file), clean it, and save it into a panda data frame
    Attributes:
        - LABEL_STUDIO_URL (url as string): the url for the label studio project you want to get your data from
        - API_KEY (string): your Label Studio API_KEY
    Returns:

## run.py
# Import the flask app from __init__.py
from digitReader import app

if __name__ == '__main__':
    # Running the app
    app.run(debug=True)

## routes.py
# Flask
from flask import render_template, request, jsonify
from digitReader import app

# Utils
import base64
from io import BytesIO

# Image Processing
import cv2

## __init__.py
# Import Flask
from flask import Flask

# Iniiate the flask app
app = Flask(__name__)
app.config['SECRET_KEY'] = 'Here you put a secret key as a string'

# Call the routes code
from digitReader import routes

## Example front-end interface.html
<!DOCTYPE html>
<html>

<head>
  <!-- Required meta tags -->
  <meta charset="utf-8">
  <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">

  <!-- Optional JavaScript -->
  <!-- jQuery first, then Popper.js, then Bootstrap JS -->

## load_trained_models.py
from keras.models import load_model

model_name_ = "Model's Name"
model = load_model(f'{PATH}/{model_name_}')

# EX : say you have the model in a folder called "models" and model's name is "myModel.model"
model_name_ = "myModel.model"
model = load_model(f'models/{model_name_}')


## rl_08-1.py
agent.tensorboard.step = episode

## rl_09.py
# Use this line to update the log file:
agent.tensorboard.update_stats(reward_avg=average_reward, reward_min=min_reward, reward_max=max_reward, epsilon=epsilon)

## rl_08.py
# Fit on all samples as one batch, log only on terminal state
self.model.fit(x = np.array(X).reshape(-1, *env.ENVIRONMENT_SHAPE),
               y = np.array(y),
               batch_size = MINIBATCH_SIZE, verbose = 0,
               shuffle=False, callbacks=[self.tensorboard] if terminal_state else None)

## rl_07.py
# Custom tensorboard object
self.tensorboard = ModifiedTensorBoard(name, log_dir="{}logs/{}-{}".format(PATH, name, int(time.time())))
	def from_label_studio_to_dataframe( LABEL_STUDIO_URL="",
	API_KEY=""):
	'''
	Goals:
	- Load the labeled data from Label Studio
	(or from a raw_data dictionary saved locally as a pickle file), clean it, and save it into a panda data frame
	Attributes:
	- LABEL_STUDIO_URL (url as string): the url for the label studio project you want to get your data from
	- API_KEY (string): your Label Studio API_KEY
	Returns:
	# Import the flask app from __init__.py
	from digitReader import app

	if __name__ == '__main__':
	# Running the app
	app.run(debug=True)
	# Flask
	from flask import render_template, request, jsonify
	from digitReader import app

	# Utils
	import base64
	from io import BytesIO

	# Image Processing
	import cv2
	# Import Flask
	from flask import Flask

	# Iniiate the flask app
	app = Flask(__name__)
	app.config['SECRET_KEY'] = 'Here you put a secret key as a string'

	# Call the routes code
	from digitReader import routes
	<!DOCTYPE html>
	<html>

	<head>
	<!-- Required meta tags -->
	<meta charset="utf-8">
	<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">

	<!-- Optional JavaScript -->
	<!-- jQuery first, then Popper.js, then Bootstrap JS -->
	from keras.models import load_model

	model_name_ = "Model's Name"
	model = load_model(f'{PATH}/{model_name_}')

	# EX : say you have the model in a folder called "models" and model's name is "myModel.model"
	model_name_ = "myModel.model"
	model = load_model(f'models/{model_name_}')
	# Use this line to update the log file:
	agent.tensorboard.update_stats(reward_avg=average_reward, reward_min=min_reward, reward_max=max_reward, epsilon=epsilon)
	# Fit on all samples as one batch, log only on terminal state
	self.model.fit(x = np.array(X).reshape(-1, *env.ENVIRONMENT_SHAPE),
	y = np.array(y),
	batch_size = MINIBATCH_SIZE, verbose = 0,
	shuffle=False, callbacks=[self.tensorboard] if terminal_state else None)
	# Custom tensorboard object
	self.tensorboard = ModifiedTensorBoard(name, log_dir="{}logs/{}-{}".format(PATH, name, int(time.time())))