library("DataExplorer")
library(nycflights13)
flights <- flights
weather <- weather
planes <- planes
airports <- airports
airlines <- airlines
create_report(flights)
##
##
## processing file: report.rmd
## | | | 0% | |. | 2% | |.. | 5% [global_options] | |... | 7% | |.... | 10% [introduce] | |.... | 12% | |..... | 14% [plot_intro] | |...... | 17% | |....... | 19% [data_structure] | |........ | 21% | |......... | 24% [missing_profile] | |.......... | 26% | |........... | 29% [univariate_distribution_header] | |........... | 31% | |............ | 33% [plot_histogram] | |............. | 36% | |.............. | 38% [plot_density] | |............... | 40% | |................ | 43% [plot_frequency_bar] | |................. | 45% | |.................. | 48% [plot_response_bar] | |.................. | 50% | |................... | 52% [plot_with_bar] | |.................... | 55% | |..................... | 57% [plot_normal_qq] | |...................... | 60% | |....................... | 62% [plot_response_qq] | |........................ | 64% | |......................... | 67% [plot_by_qq] | |.......................... | 69% | |.......................... | 71% [correlation_analysis] | |........................... | 74% | |............................ | 76% [principal_component_analysis] | |............................. | 79% | |.............................. | 81% [bivariate_distribution_header] | |............................... | 83% | |................................ | 86% [plot_response_boxplot] | |................................. | 88% | |................................. | 90% [plot_by_boxplot] | |.................................. | 93% | |................................... | 95% [plot_response_scatterplot] | |.................................... | 98% | |.....................................| 100% [plot_by_scatterplot]
## output file: /Users/josemarentes/Documents/ITESM 2/SEGUNDO/Rstudio/report.knit.md
## /Applications/RStudio.app/Contents/Resources/app/quarto/bin/tools/aarch64/pandoc +RTS -K512m -RTS '/Users/josemarentes/Documents/ITESM 2/SEGUNDO/Rstudio/report.knit.md' --to html4 --from markdown+autolink_bare_uris+tex_math_single_backslash --output pandoca6651e1d12a.html --lua-filter /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/rmarkdown/rmarkdown/lua/pagebreak.lua --lua-filter /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/rmarkdown/rmarkdown/lua/latex-div.lua --embed-resources --standalone --variable bs3=TRUE --section-divs --table-of-contents --toc-depth 6 --template /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/rmarkdown/rmd/h/default.html --no-highlight --variable highlightjs=1 --variable theme=yeti --mathjax --variable 'mathjax-url=https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML' --include-in-header /var/folders/9q/6mpw0h3x42z6w2qvfpm78f740000gn/T//RtmpYl0O21/rmarkdown-stra66273a0414.html
##
## Output created: report.html
introduce(flights) # Resumen general del conjunto de datos
## # A tibble: 1 × 9
## rows columns discrete_columns continuous_columns all_missing_columns
## <int> <int> <int> <int> <int>
## 1 336776 19 5 14 0
## # ℹ 4 more variables: total_missing_values <int>, complete_rows <int>,
## # total_observations <int>, memory_usage <dbl>
plot_intro(flights) # Distribución de los tipos de datos
plot_boxplot(flights, by = "carrier") # Boxplot por categorÃa (especificando una columna)
## Warning: Removed 44083 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
plot_missing(flights) # Visualización de los datos faltantes
plot_histogram(flights) # Histogramas de las variables numéricas
plot_bar(flights) # Gráficos de barras para variables categóricas
## 3 columns ignored with more than 50 categories.
## tailnum: 4044 categories
## dest: 105 categories
## time_hour: 6936 categories
plot_correlation(flights) # Matriz de correlación para variables numéricas
## 3 features with more than 20 categories ignored!
## tailnum: 4044 categories
## dest: 105 categories
## time_hour: 6936 categories
## Warning in cor(x = structure(list(year = c(2013L, 2013L, 2013L, 2013L, 2013L, :
## the standard deviation is zero
