ivopbernardo

# Load h2o
library(h2o)
library(ggplot2)

# Load Dataset - London Bike 
london_bike <- read.csv('./london_merged.csv')

# Transforming Weather code and Season to factor
london_bike$weather_code <- as.factor(london_bike$weather_code)
london_bike$season <- as.factor(london_bike$season)

ivopbernardo

# caret library example used in blogpost:
# https://towardsdatascience.com/a-guide-to-using-caret-in-r-71dec0bda208

library(caTools)
library(caret)

# Train Test Split on both Iris and Mtcars

train_test_split <- function(df) {
  set.seed(42)

ivopbernardo

# R Function Best Practices used in blog post:
# https://towardsdatascience.com/writing-better-r-functions-best-practices-and-tips-d48ef0691c24

library(ggplot2)

#----------------------------------#

# Function Indentation

# Proper Indentation - Bad Example

ivopbernardo

# mlr library example clode - used in blog post: 
# https://towardsdatascience.com/decision-tree-hyperparameter-tuning-in-r-using-mlr-3248bfd2d88c

titanic <- read.csv('train.csv')

library(dplyr)
library(rpart)
library(rpart.plot)
library(Metrics)
library(mlr)

ivopbernardo

# dplyr library example used in blog post:
# https://towardsdatascience.com/8-cool-dplyr-function-to-learn-in-r-8736d7fa899c

library(dplyr)

starwars_df <- starwars

# Filter using Dplyr
filter_droids <- starwars %>%
  filter(species == 'Droid')

ivopbernardo

import rasterio
from rasterio.plot import show
 
url = "zip+file:data/mdt.zip!mdt.tif"
lisbon_elevation = rasterio.open(url)

# Plot the raster data to get a sense of it
show(lisbon_elevation, cmap="terrain")

# Get the elevation from the raster data

ivopbernardo

# Read the metro data
metro = pd.read_csv(Path("data", "metro_stations.csv"))

# Convert to a GeoDataFrame
metro = gpd.GeoDataFrame(
    metro,
    geometry=gpd.points_from_xy(metro.longitude, metro.latitude),
    crs="epsg:4326"
).to_crs(epsg=3857)

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))

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

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",
)