Prediction_Model ($29) · Snippets · Snippets

import glob
import pickle
from flask import Flask, request
from flasgger import Swagger
import numpy as np
import pandas as pd
import os, fnmatch

#location of saved prediction model for pickle library format
with open('./randomforest2model.pkl', 'rb') as model_file:
    model = pickle.load(model_file)

app = Flask(__name__,)
swagger = Swagger(app)

@app.route('/predict')
def predictor_EEG():
    """Example file endpoint returning a prediction of iris
    ---
    parameters:
      -name: input_file
       in: formData
       type: file
       required: true
    """

    predictions = []

    listOfFiles = os.listdir('/home/nazmi')
    pattern = "*.csv"
    # BUYUK
    last_file = listOfFiles[len(listOfFiles) - 1]
    print("last file {}".format(last_file))

    for entry in [last_file]:
        if fnmatch.fnmatch(entry, pattern):
            read_File = pd.read_csv(entry, usecols = range(1, 5))
            print (read_File)
            #checks only the last row of the csv file to do prediction models,

            last_row = read_File.tail(20)
            prediction = model.predict(last_row)

            # append to list of predictions
            predictions.append(prediction)


    html = """"
    <html>
    <head>
    <title>Emotion Classification Page</title>
    <meta http-equiv="refresh" content="5" >
    </head>
    <body>
    <h1>This is a model representation of emotional space</h1>
    <h2>The last value on the right represents your current emotional state</h2>
    <p>Value "0" = Happy</p>
    <p>Value "1" = Scared</p>
    <p>Value "2" = Bored</p>
    <p>Value "3" = Calm</p>
    <img src="/static/Pictures/Slide1.PNG" width="50%" height="50%">
    <p>Predicted Emotion = {}</p>
    </body>
    </html>
    """.format(str(predictions))

    return html


if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5000)