keitazoumana

pip install tweepy

keitazoumana

import tweepy
import pandas as pd
import nltk
from tweepy import OAuthHandler
from tweepy import Cursor

keitazoumana

"""
Content of preprocess_data.py
"""
from sklearn.model_selection import train_test_split
import pandas as pd 

def prepare_data(path_to_data):

    # Read data from path
    data = pd.read_csv(path_to_data)

keitazoumana

"""
Content of train_model.py
"""
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report
import pickle

def run_model_training(X_train, X_test, y_train, y_test):
    clf = LogisticRegression()
    clf.fit(X_train,y_train)

keitazoumana

"""
Content of run_training.py
"""

import joblib

# Get customized functions from library
from packages.preprocess_data import *
from packages.train_model import run_model_training

keitazoumana

import slate3k as slate
text  = slate.PDF(open('./data/obama-worlds-matter.pdf', 'rb')).text()
print(text)

keitazoumana

from pdfminer.high_level import extract_text
text  = extract_text('./data/obama-worlds-matter.pdf', 'rb')
print(text)

keitazoumana

from PyPDF2 import PdfFileReader

# creating a pdf file object
pdfObject = open('./data/obama-worlds-matter.pdf', 'rb')

# creating a pdf reader object
pdfReader = PdfFileReader(pdfObject)

# Extract and concatenate each page's content
text=''

keitazoumana

from tabula import read_pdf
from tabulate import tabulate
import pandas as pd
import io

# Read the only the page n°6 of the file
food_calories = read_pdf('./data/food_calories.pdf',pages = 6, 
                         multiple_tables = True, stream = True)

# Transform the result into a string table format

keitazoumana

import tabula

tabula.convert_into('./data/food_calories.pdf', "./data/food_calories2.csv", 
                    output_format="csv", pages = 6)