ivopbernardo

import pandas as pd
import pyodbc

#Ask for user and password input 

user = input('Provide user: \n')
pwd = input('Provide password: \n')

#Make connection to My SQL local host
mydb = pyodbc.connect("DRIVER={MySQL ODBC 8.0 ANSI Driver}; SERVER=localhost; PORT=3306;DATABASE=sakila; UID=%s; PASSWORD=%s;" % (user, pwd)) 

ivopbernardo

# Loading readxl library
library(readxl)

clean_crime_data <- function(path) {
  # Load the Data
  crime_data <- read_xls(path)
  
  # Assigning colnames
  colnames(crime_data) <- crime_data[3,]
  

ivopbernardo

# Import sklearn vectorizers and pandas
import pandas as pd
from sklearn.feature_extraction.text import (
  CountVectorizer, 
  TfidfVectorizer
)


# Defining our sentence examples
sentence_list = [

ivopbernardo

from nltk.tokenize import word_tokenize
from nltk.stem import PorterStemmer, SnowballStemmer, LancasterStemmer

porter = PorterStemmer()
snowball = SnowballStemmer(language='english')
lanc = LancasterStemmer()

sentence_example = (
  'This is definitely a controversy as the attorney labeled the case "extremely controversial"'
)

ivopbernardo

import wikipedia
import pandas as pd
import numpy as np
import string
from nltk.tokenize import word_tokenize
from sklearn.metrics.pairwise import cosine_similarity

def retrieve_page(page_name: str) -> list:
    '''
    Retrieves page data from wikipedia

ivopbernardo

# Don't forget to download the train.csv file
# to make this gist work.

# Download it at: https://www.kaggle.com/c/titanic/data?select=train.csv

# You also need to install ROCR and rpart libraries

# Reading the titanic train dataset
titanic <- read.csv('./train.csv')

ivopbernardo

# Getting Latitude and Longitude from Nominatim

from geopy.geocoders import Nominatim
from geopy.extra.rate_limiter import RateLimiter

geocoder = Nominatim(user_agent="FindAddress")
geocode = RateLimiter(
    geocoder.geocode,
    min_delay_seconds = 1,
    return_value_on_exception = None

ivopbernardo

import geopandas as gpd

house_data_gdf = gpd.GeoDataFrame(
    house_data,
    geometry=gpd.points_from_xy(
       house_data.longitude,
       house_data.latitude
    ),
    crs="epsg:4326",
)

ivopbernardo

# Read data directly from the portuguese gov website.
parishes_url = "zip+https://dados.gov.pt/s/resources/freguesias-de-portugal/20181112-195834/cont-aad-caop2017.zip"
parishes = gpd.read_file(parishes_url)

# Left Join the house data to the parishes data, if house is `within` parish.
house_data_gdf = gpd.sjoin(house_data_gdf, parishes, how="left", op="within")

ivopbernardo

# Public Hospitals in Lisbon
hospitals_url = "https://opendata.arcgis.com/datasets/172678f193144512860a397fde991361_4.geojson" # GeoJSON
hospitals_gdf = gpd.read_file(hospitals_url).to_crs(epsg=3857)
hospitals_gdf.head()

# Buffer the house locations by 1km
house_data_gdf_buffer = (
   house_data_gdf
   .copy()
   .assign(geometry_buffer = lambda d: d.buffer(1000))