Publications by Data Science in Foco

Regressao_Tidymodels_Recipes_Workflow

07.08.2020

library(tidymodels) library(tidyverse) library(themis) Dados df <- read.csv("C:\\Data Science\\CSV\\module_5_auto.csv", stringsAsFactors = T) %>% select(-horsepower.binned) rmarkdown::paged_table(head(df)) Separação conjunto treino e teste df_split <- initial_split(df, prop=0.85) # dividindo os dados em 85% para treino e 15% para tes...

177 sym R (1507 sym/9 pcs)

DataWrangling/Tidymodels/Recipes

08.08.2020

Introdução A base de dados utilizada está no UCI Machine Learning Repository link: Informações do conjunto de dados: Esse conjunto de dados consiste em três tipos de entidades: (a) a especificação de um automóvel em termos de várias características. (b) sua classificação de risco de furto. (c) suas perdas normalizadas de uso em comp...

3965 sym R (7534 sym/10 pcs) 1 img

Hyperparameter Fine Tunning Xgboost

07.01.2021

1 Importing Needed packages library(tidyverse) library(kableExtra) library(htmltools) library(Metrics) library(tidymodels) library(timetk) library(doParallel) 1.1 Helper Functions minmax_scaler <- function(x) { return( ( x - min( x ) ) / ( max(x) - min(x) ) ) } robust_scaler <- function(x){ return( ( x - quantile( x , 0.5) ) ...

2286 sym R (10684 sym/24 pcs)

Modelling Preidict

30.11.2020

1 Importing Needed packages 1.1 Helper functions 1.2 Reading the data X.U.FEFF.key fare_amount pickup_datetime pickup_longitude pickup_latitude dropoff_longitude dropoff_latitude passenger_count 2011-06-21 16:15:00.00000073 7.3 2011-06-21 16:15:00 UTC -73.99187 40.75444 -73.97723 40.77432 3 2009-06-06 23:56:00.0...

17187 sym R (6339 sym/14 pcs) 6 img

EDA Taxi Fare in New York

25.11.2020

1 Importing Needed packages 2 Helper Function 2.1 Reading the data Data / Dados fare_amount pickup_datetime pickup_longitude pickup_latitude dropoff_longitude dropoff_latitude passenger_count hour_of_day days_of_week day_of_year day year travelled_distance_km month_fare is_pickup_jfk is_dropoff_jfk is_pickup_e...

7351 sym R (1937 sym/3 pcs) 15 img

Modelling Preidict

09.12.2020

1 Importing Needed packages 1.1 Helper Functions ml_error <- function(model_name = "Linear Regression Model",model_predictions){ MAE <- model_predictions %>% yardstick::mae(actual, predictions) MAPE <- lm_pred %>% yardstick::mape(actual, predictions) RMSE <- lm_pred %>% yardstick::rmse(actual, predictions) data.fra...

4928 sym R (10664 sym/24 pcs) 1 img

Sales forecast next 6 weeks

09.01.2021

1 Importing Needed packages library(tidyverse) library(lubridate) library(e1071) library(gridExtra) library(janitor) library(data.table) library(funModeling) library(kableExtra) library(htmltools) library(ISOweek) library(vcd) library(plotly) library(timetk) library(ggpubr) theme_set(theme_minimal()) 1.1 Helper Functions catcor <-...

7841 sym R (27818 sym/62 pcs) 21 img 11 tbl