tcramm0nd

import os
import io
import requests
import zipfile

def boundary_file_downloader(year=2019, state='us', entity='state', resolution='500k', filetype='shp', path=None):
    """Downloads US Census Bureau Cartographoc Boundary files to a dedicated folder.

    Args:
        year (int, optional): Year the data should be pulled from. Defaults to 2019.

tcramm0nd

import pandas as pd

# Initialize the paramaters of the loan
loan_amount = 18000
apr = 5.29
loan_term = 60

# Get a monthly percentage rate
apr /= 100
mpr = apr / 12

tcramm0nd

# A breif overview of how to how to import an SHP file to a Geopandas DataFrame. For a more detailed breakdown of the
#process you can find the original post here: http://timcrammond.com/blog/creating-a-geopandas-dataframe-from-a-shp-file

import shapefile
import geopandas as gpd
from shapely.geometry import shape
import osr

tracts = shapefile.Reader('data/cb_2018_42_tract_500k.shp')

tcramm0nd

# A breif overview of how to create a Random Forest Classifier using Scikit-Learn. For a more detailed breakdown and 
# an overview of what a Random Forest is, you can find the original post here: http://timcrammond.com/blog/what-is-random-forest/
from sklearn import datasets, metrics
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier

wine = datasets.load_wine()

X = wine.data
y = wine.target

tcramm0nd

def text_preprocessing(text):
    '''This is a pretty basic NLP text cleaner that takes in a corpus/text, 
    applies some cleaning functions to remove undesirable
    characters, and returns the text in the same format
    
    This requires the following to be imported:
    re
    nltk
    '''
    # text cleaning