stackoverflow challenge 2023
2023-11-13
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
#install.packages("readr")
library(readr)
data <- read_csv("Stackoverflow2.csv")## Warning: One or more parsing issues, call `problems()` on your data frame for details,
## e.g.:
## dat <- vroom(...)
## problems(dat)## Rows: 89184 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (5): Dev_type, YearsCodePro, edlevel, country, CompTotal
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.summary(lm(CompTotal~ factor(Dev_type) + factor(country) + factor(YearsCodePro) + factor(edlevel), data = data))##
## Call:
## lm(formula = CompTotal ~ factor(Dev_type) + factor(country) +
## factor(YearsCodePro) + factor(edlevel), data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.609e+17 -8.008e+15 3.248e+15 1.873e+16 9.996e+20
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -4.128e+14 9.129e+16 -0.005 0.996
## factor(Dev_type)1 -1.221e+16 6.387e+16 -0.191 0.848
## factor(Dev_type)2 5.998e+16 5.278e+16 1.137 0.256
## factor(Dev_type)3 -1.056e+16 4.834e+16 -0.218 0.827
## factor(Dev_type)4 -6.445e+15 4.585e+16 -0.141 0.888
## factor(country)1 -1.684e+16 2.818e+16 -0.597 0.550
## factor(YearsCodePro)1 -5.960e+15 5.917e+16 -0.101 0.920
## factor(YearsCodePro)2 -7.265e+15 5.938e+16 -0.122 0.903
## factor(YearsCodePro)3 -7.036e+15 5.974e+16 -0.118 0.906
## factor(YearsCodePro)4 -7.791e+15 6.207e+16 -0.126 0.900
## factor(YearsCodePro)5 -6.901e+15 5.800e+16 -0.119 0.905
## factor(YearsCodePro)6 -6.352e+15 6.419e+16 -0.099 0.921
## factor(YearsCodePro)7 -6.974e+15 6.516e+16 -0.107 0.915
## factor(YearsCodePro)8 2.824e+17 6.543e+16 4.316 1.59e-05 ***
## factor(YearsCodePro)9 -5.814e+15 7.925e+16 -0.073 0.942
## factor(YearsCodePro)10 -4.822e+15 5.896e+16 -0.082 0.935
## factor(YearsCodePro)11 -6.304e+15 8.134e+16 -0.077 0.938
## factor(YearsCodePro)12 -4.027e+15 7.555e+16 -0.053 0.957
## factor(YearsCodePro)13 -5.001e+15 8.767e+16 -0.057 0.955
## factor(YearsCodePro)14 -4.442e+15 9.995e+16 -0.044 0.965
## factor(YearsCodePro)15 -3.269e+15 7.107e+16 -0.046 0.963
## factor(YearsCodePro)16 -4.638e+15 9.917e+16 -0.047 0.963
## factor(YearsCodePro)17 -4.337e+15 1.041e+17 -0.042 0.967
## factor(YearsCodePro)18 -4.324e+15 1.015e+17 -0.043 0.966
## factor(YearsCodePro)19 -3.033e+15 1.355e+17 -0.022 0.982
## factor(YearsCodePro)20 -2.882e+14 7.768e+16 -0.004 0.997
## factor(YearsCodePro)21 -4.773e+15 1.446e+17 -0.033 0.974
## factor(YearsCodePro)22 -2.173e+15 1.196e+17 -0.018 0.986
## factor(YearsCodePro)23 -9.128e+14 1.054e+17 -0.009 0.993
## factor(YearsCodePro)24 -1.619e+15 1.318e+17 -0.012 0.990
## factor(YearsCodePro)25 6.726e+14 9.346e+16 0.007 0.994
## factor(YearsCodePro)26 -5.494e+14 1.553e+17 -0.004 0.997
## factor(YearsCodePro)27 -2.076e+15 1.546e+17 -0.013 0.989
## factor(YearsCodePro)28 2.712e+15 1.671e+17 0.016 0.987
## factor(YearsCodePro)29 -1.545e+15 2.297e+17 -0.007 0.995
## factor(YearsCodePro)30 3.817e+15 1.146e+17 0.033 0.973
## factor(YearsCodePro)31 1.424e+15 2.471e+17 0.006 0.995
## factor(YearsCodePro)32 -1.922e+15 1.983e+17 -0.010 0.992
## factor(YearsCodePro)33 3.479e+15 2.086e+17 0.017 0.987
## factor(YearsCodePro)34 1.399e+15 2.538e+17 0.006 0.996
## factor(YearsCodePro)35 4.697e+15 1.589e+17 0.030 0.976
## factor(YearsCodePro)36 -5.643e+13 2.389e+17 0.000 1.000
## factor(YearsCodePro)37 4.298e+15 2.753e+17 0.016 0.988
## factor(YearsCodePro)38 5.968e+15 2.636e+17 0.023 0.982
## factor(YearsCodePro)39 3.073e+15 3.382e+17 0.009 0.993
## factor(YearsCodePro)40 5.450e+15 1.871e+17 0.029 0.977
## factor(YearsCodePro)41 3.524e+15 3.782e+17 0.009 0.993
## factor(YearsCodePro)42 9.733e+15 3.736e+17 0.026 0.979
## factor(YearsCodePro)43 6.801e+15 4.105e+17 0.017 0.987
## factor(YearsCodePro)44 5.825e+15 5.181e+17 0.011 0.991
## factor(YearsCodePro)45 1.240e+16 3.331e+17 0.037 0.970
## factor(YearsCodePro)46 4.544e+15 5.839e+17 0.008 0.994
## factor(YearsCodePro)47 6.229e+15 6.846e+17 0.009 0.993
## factor(YearsCodePro)48 1.607e+16 6.125e+17 0.026 0.979
## factor(YearsCodePro)49 9.379e+15 8.961e+17 0.010 0.992
## factor(YearsCodePro)50 8.964e+15 6.847e+17 0.013 0.990
## factor(edlevel)1 4.128e+14 1.327e+17 0.003 0.998
## factor(edlevel)2 3.383e+15 1.171e+17 0.029 0.977
## factor(edlevel)3 2.910e+14 9.455e+16 0.003 0.998
## factor(edlevel)4 -2.835e+15 9.294e+16 -0.031 0.976
## factor(edlevel)5 -4.187e+15 1.083e+17 -0.039 0.969
## factor(edlevel)6 1.889e+16 8.981e+16 0.210 0.833
## factor(edlevel)7 -1.237e+16 9.133e+16 -0.135 0.892
## factor(edlevel)8 -5.747e+15 1.036e+17 -0.055 0.956
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.351e+18 on 89037 degrees of freedom
## (83 observations deleted due to missingness)
## Multiple R-squared: 0.0003497, Adjusted R-squared: -0.0003577
## F-statistic: 0.4943 on 63 and 89037 DF, p-value: 0.9997#plot
library(ggplot2)
# Load packages
require(MASS) # to access Animals data sets## Loading required package: MASSrequire(scales) # to access break formatting functions## Loading required package: scales##
## Attaching package: 'scales'## The following object is masked from 'package:readr':
##
## col_factorp2 <- ggplot(data, aes(x=YearsCodePro, y=CompTotal, color=edlevel)) + geom_point() +
scale_y_log10(breaks = trans_breaks("log10", function(x) 10^x),
labels = trans_format("log10", math_format(10^.x))) +
theme_bw()
p2## Warning: Transformation introduced infinite values in continuous y-axis## Warning: Removed 83 rows containing missing values (`geom_point()`).