andrea-dagostino

# let's create the dataset with time windows
dataset = windowed_dataset(series_train)

# we divide into training and validation set
time_train, series_train, time_valid, series_valid = train_val_split(G.TIME, G.SERIES)

andrea-dagostino

def fuzzy_tagging(tags, articles):
	"""
	This function receives as input a list of predefined tags and the list of textual content to be tagged.
  Returns a Pandas dataframe with the articles tagged
	"""
	results = []
	# iterate through tags
	for i, tag in enumerate(tags):
	    d = {}
	    ranking = process.extract(tag, articles, limit=4) # extract the tag, ranking the 4 articles most representative

andrea-dagostino

import numpy as np

from google.colab import files
from keras.preprocessing import image

uploaded = files.upload()

for fn in uploaded.keys():
 
  # prediction on the uploaded image

andrea-dagostino

# output layer
layers.Dense(2, activation="softmax", name="output")

andrea-dagostino

# output layer
layers.Dense(1, name="output")

andrea-dagostino

model = keras.Sequential(
    [
	layers.Dense(256, input_dim=4, activation="relu", name="input")
        layers.Dense(128, activation="relu", name="layer1"),
        layers.Dense(64, activation="relu", name="layer2"),
        # ...
    ]
)

andrea-dagostino

# input layer
layers.Dense(256, input_dim=4, activation="relu", name="input")

andrea-dagostino

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

model = keras.Sequential(
	# [...] 
)

andrea-dagostino

# upload the dataset and isolate posts
df = pd.read_csv('dataset.csv')
posts = df[df.url.str.contains('post')]
posts.reset_index(inplace=True, drop=True)
articles = list(posts.article)

andrea-dagostino

# these are the tags we want to apply to our documents.
# change this list at your discretion
tags = [
    "machine learning",
    "clustering",
    "carriera", # "career" in ita
    "progetto", # "project" in ita
    "consigli", # "tips" in ita
    "analytics",
    "deep learning",