sklearn_model = SKLearnModel(model_data="s3://bucket/model.tar.gz", role="SageMakerRole", entry_point="predict.py")

import os
import re
import pickle
import numpy as np
import pandas as pd
import nltk
nltk.download("stopwords")
from nltk.corpus import stopwords
from nltk.stem.porter import *
from bs4 import BeautifulSoup
import sagemaker_containers

from sklearn.feature_extraction.text import CountVectorizer



def model_fn(model_dir):

    #TODO How to load the word_dict.
    #TODO How to load the model.
    return model, word_dict

def predict_fn(input_data, model):
    print('Inferring sentiment of input data.')
    trained_model, word_dict = model
    if word_dict is None:
        raise Exception('Model has not been loaded properly, no word_dict.')

    #Process input_data so that it is ready to be sent to our model.

    input_bow_csv = process_input_text(word_dict, input_data)
    prediction = trained_model.predict(input_bow_csv)
    return prediction


def process_input_text(word_dict, input_data):

    words = text_to_words(input_data);
    vectorizer = CountVectorizer(preprocessor=lambda x: x, tokenizer=lambda x: x, word_dict)
    bow_array = vectorizer.transform([words]).toarray()[0]
    bow_csv = ",".join(str(bit) for bit in bow_array)
    return bow_csv

def text_to_words(text):
    """
    Uses the Porter Stemmer to stem words in a review
    """
    #instantiate stemmer
    stemmer = PorterStemmer()
    text_nohtml = BeautifulSoup(text, "html.parser").get_text() # Remove HTML tags
    text_lower = re.sub(r"[^a-zA-Z0-9]", " ", text_nohtml.lower()) # Convert to lower case
    words = text_lower.split() # Split string into words
    words = [w for w in words if w not in stopwords.words("english")] # Remove stopwords
    words = [PorterStemmer().stem(w) for w in words] # stem
    return words

def input_fn(input_data, content_type):
    return input_data;

def output_fn(prediction_output, accept):
    return prediction_output;