Generate summary statistics & frequency table for all continuous variables in data.
Examples
# all columns
ds_auto_summary_stats(mtcarz)
#> -------------------------------- Variable: mpg --------------------------------
#>
#> ------------------------------ Summary Statistics ------------------------------
#>
#> -------------------------------- Variable: mpg --------------------------------
#>
#> Univariate Analysis
#>
#> N 32.00 Variance 36.32
#> Missing 0.00 Std Deviation 6.03
#> Mean 20.09 Range 23.50
#> Median 19.20 Interquartile Range 7.38
#> Mode 10.40 Uncorrected SS 14042.31
#> Trimmed Mean 19.95 Corrected SS 1126.05
#> Skewness 0.67 Coeff Variation 30.00
#> Kurtosis -0.02 Std Error Mean 1.07
#>
#> Quantiles
#>
#> Quantile Value
#>
#> Max 33.90
#> 99% 33.44
#> 95% 31.30
#> 90% 30.09
#> Q3 22.80
#> Median 19.20
#> Q1 15.43
#> 10% 14.34
#> 5% 12.00
#> 1% 10.40
#> Min 10.40
#>
#> Extreme Values
#>
#> Low High
#>
#> Obs Value Obs Value
#> 15 10.4 20 33.9
#> 16 10.4 18 32.4
#> 24 13.3 19 30.4
#> 7 14.3 28 30.4
#> 17 14.7 26 27.3
#>
#>
#>
#> NULL
#>
#>
#> ---------------------------- Frequency Distribution ----------------------------
#>
#> Variable: mpg
#> |-----------------------------------------------------------------------|
#> | Bins | Frequency | Cum Frequency | Percent | Cum Percent |
#> |-----------------------------------------------------------------------|
#> | 10.4 - 15.1 | 6 | 6 | 18.75 | 18.75 |
#> |-----------------------------------------------------------------------|
#> | 15.1 - 19.8 | 12 | 18 | 37.5 | 56.25 |
#> |-----------------------------------------------------------------------|
#> | 19.8 - 24.5 | 8 | 26 | 25 | 81.25 |
#> |-----------------------------------------------------------------------|
#> | 24.5 - 29.2 | 2 | 28 | 6.25 | 87.5 |
#> |-----------------------------------------------------------------------|
#> | 29.2 - 33.9 | 4 | 32 | 12.5 | 100 |
#> |-----------------------------------------------------------------------|
#> | Total | 32 | - | 100.00 | - |
#> |-----------------------------------------------------------------------|
#>
#>
#> -------------------------------- Variable: disp --------------------------------
#>
#> ------------------------------ Summary Statistics ------------------------------
#>
#> -------------------------------- Variable: disp --------------------------------
#>
#> Univariate Analysis
#>
#> N 32.00 Variance 15360.80
#> Missing 0.00 Std Deviation 123.94
#> Mean 230.72 Range 400.90
#> Median 196.30 Interquartile Range 205.18
#> Mode 275.80 Uncorrected SS 2179627.47
#> Trimmed Mean 228.00 Corrected SS 476184.79
#> Skewness 0.42 Coeff Variation 53.72
#> Kurtosis -1.07 Std Error Mean 21.91
#>
#> Quantiles
#>
#> Quantile Value
#>
#> Max 472.00
#> 99% 468.28
#> 95% 449.00
#> 90% 396.00
#> Q3 326.00
#> Median 196.30
#> Q1 120.83
#> 10% 80.61
#> 5% 77.35
#> 1% 72.53
#> Min 71.10
#>
#> Extreme Values
#>
#> Low High
#>
#> Obs Value Obs Value
#> 20 71.1 15 472
#> 19 75.7 16 460
#> 18 78.7 17 440
#> 26 79 25 400
#> 28 95.1 5 360
#>
#>
#>
#> NULL
#>
#>
#> ---------------------------- Frequency Distribution ----------------------------
#>
#> Variable: disp
#> |---------------------------------------------------------------------------|
#> | Bins | Frequency | Cum Frequency | Percent | Cum Percent |
#> |---------------------------------------------------------------------------|
#> | 71.1 - 151.3 | 12 | 12 | 37.5 | 37.5 |
#> |---------------------------------------------------------------------------|
#> | 151.3 - 231.5 | 5 | 17 | 15.62 | 53.12 |
#> |---------------------------------------------------------------------------|
#> | 231.5 - 311.6 | 6 | 23 | 18.75 | 71.88 |
#> |---------------------------------------------------------------------------|
#> | 311.6 - 391.8 | 5 | 28 | 15.62 | 87.5 |
#> |---------------------------------------------------------------------------|
#> | 391.8 - 472 | 4 | 32 | 12.5 | 100 |
#> |---------------------------------------------------------------------------|
#> | Total | 32 | - | 100.00 | - |
#> |---------------------------------------------------------------------------|
#>
#>
#> --------------------------------- Variable: hp ---------------------------------
#>
#> ------------------------------ Summary Statistics ------------------------------
#>
#> --------------------------------- Variable: hp ---------------------------------
#>
#> Univariate Analysis
#>
#> N 32.00 Variance 4700.87
#> Missing 0.00 Std Deviation 68.56
#> Mean 146.69 Range 283.00
#> Median 123.00 Interquartile Range 83.50
#> Mode 110.00 Uncorrected SS 834278.00
#> Trimmed Mean 143.57 Corrected SS 145726.88
#> Skewness 0.80 Coeff Variation 46.74
#> Kurtosis 0.28 Std Error Mean 12.12
#>
#> Quantiles
#>
#> Quantile Value
#>
#> Max 335.00
#> 99% 312.99
#> 95% 253.55
#> 90% 243.50
#> Q3 180.00
#> Median 123.00
#> Q1 96.50
#> 10% 66.00
#> 5% 63.65
#> 1% 55.10
#> Min 52.00
#>
#> Extreme Values
#>
#> Low High
#>
#> Obs Value Obs Value
#> 19 52 31 335
#> 8 62 29 264
#> 20 65 7 245
#> 18 66 24 245
#> 26 66 17 230
#>
#>
#>
#> NULL
#>
#>
#> ---------------------------- Frequency Distribution ----------------------------
#>
#> Variable: hp
#> |-------------------------------------------------------------------------|
#> | Bins | Frequency | Cum Frequency | Percent | Cum Percent |
#> |-------------------------------------------------------------------------|
#> | 52 - 108.6 | 10 | 10 | 31.25 | 31.25 |
#> |-------------------------------------------------------------------------|
#> | 108.6 - 165.2 | 9 | 19 | 28.12 | 59.38 |
#> |-------------------------------------------------------------------------|
#> | 165.2 - 221.8 | 8 | 27 | 25 | 84.38 |
#> |-------------------------------------------------------------------------|
#> | 221.8 - 278.4 | 4 | 31 | 12.5 | 96.88 |
#> |-------------------------------------------------------------------------|
#> | 278.4 - 335 | 1 | 32 | 3.12 | 100 |
#> |-------------------------------------------------------------------------|
#> | Total | 32 | - | 100.00 | - |
#> |-------------------------------------------------------------------------|
#>
#>
#> -------------------------------- Variable: drat --------------------------------
#>
#> ------------------------------ Summary Statistics ------------------------------
#>
#> -------------------------------- Variable: drat --------------------------------
#>
#> Univariate Analysis
#>
#> N 32.00 Variance 0.29
#> Missing 0.00 Std Deviation 0.53
#> Mean 3.60 Range 2.17
#> Median 3.70 Interquartile Range 0.84
#> Mode 3.07 Uncorrected SS 422.79
#> Trimmed Mean 3.58 Corrected SS 8.86
#> Skewness 0.29 Coeff Variation 14.87
#> Kurtosis -0.45 Std Error Mean 0.09
#>
#> Quantiles
#>
#> Quantile Value
#>
#> Max 4.93
#> 99% 4.78
#> 95% 4.31
#> 90% 4.21
#> Q3 3.92
#> Median 3.70
#> Q1 3.08
#> 10% 3.01
#> 5% 2.85
#> 1% 2.76
#> Min 2.76
#>
#> Extreme Values
#>
#> Low High
#>
#> Obs Value Obs Value
#> 6 2.76 19 4.93
#> 22 2.76 27 4.43
#> 15 2.93 20 4.22
#> 16 3 29 4.22
#> 12 3.07 32 4.11
#>
#>
#>
#> NULL
#>
#>
#> ---------------------------- Frequency Distribution ----------------------------
#>
#> Variable: drat
#> |-------------------------------------------------------------------------|
#> | Bins | Frequency | Cum Frequency | Percent | Cum Percent |
#> |-------------------------------------------------------------------------|
#> | 2.8 - 3.2 | 11 | 11 | 34.38 | 34.38 |
#> |-------------------------------------------------------------------------|
#> | 3.2 - 3.6 | 4 | 15 | 12.5 | 46.88 |
#> |-------------------------------------------------------------------------|
#> | 3.6 - 4.1 | 10 | 25 | 31.25 | 78.12 |
#> |-------------------------------------------------------------------------|
#> | 4.1 - 4.5 | 6 | 31 | 18.75 | 96.88 |
#> |-------------------------------------------------------------------------|
#> | 4.5 - 4.9 | 1 | 32 | 3.12 | 100 |
#> |-------------------------------------------------------------------------|
#> | Total | 32 | - | 100.00 | - |
#> |-------------------------------------------------------------------------|
#>
#>
#> --------------------------------- Variable: wt ---------------------------------
#>
#> ------------------------------ Summary Statistics ------------------------------
#>
#> --------------------------------- Variable: wt ---------------------------------
#>
#> Univariate Analysis
#>
#> N 32.00 Variance 0.96
#> Missing 0.00 Std Deviation 0.98
#> Mean 3.22 Range 3.91
#> Median 3.33 Interquartile Range 1.03
#> Mode 3.44 Uncorrected SS 360.90
#> Trimmed Mean 3.20 Corrected SS 29.68
#> Skewness 0.47 Coeff Variation 30.41
#> Kurtosis 0.42 Std Error Mean 0.17
#>
#> Quantiles
#>
#> Quantile Value
#>
#> Max 5.42
#> 99% 5.40
#> 95% 5.29
#> 90% 4.05
#> Q3 3.61
#> Median 3.33
#> Q1 2.58
#> 10% 1.96
#> 5% 1.74
#> 1% 1.54
#> Min 1.51
#>
#> Extreme Values
#>
#> Low High
#>
#> Obs Value Obs Value
#> 27 1.51 15 5.42
#> NA 1.61 12 5.34
#> NA 1.83 NA 5.25
#> NA 1.94 NA 4.07
#> NA 2.14 NA 3.85
#>
#>
#>
#> NULL
#>
#>
#> ---------------------------- Frequency Distribution ----------------------------
#>
#> Variable: wt
#> |---------------------------------------------------------------------------|
#> | Bins | Frequency | Cum Frequency | Percent | Cum Percent |
#> |---------------------------------------------------------------------------|
#> | 1.5 - 2.3 | 6 | 6 | 18.75 | 18.75 |
#> |---------------------------------------------------------------------------|
#> | 2.3 - 3.1 | 6 | 12 | 18.75 | 37.5 |
#> |---------------------------------------------------------------------------|
#> | 3.1 - 3.9 | 16 | 28 | 50 | 87.5 |
#> |---------------------------------------------------------------------------|
#> | 3.9 - 4.6 | 1 | 29 | 3.12 | 90.62 |
#> |---------------------------------------------------------------------------|
#> | 4.6 - 5.4 | 3 | 32 | 9.38 | 100 |
#> |---------------------------------------------------------------------------|
#> | Total | 32 | - | 100.00 | - |
#> |---------------------------------------------------------------------------|
#>
#>
#> -------------------------------- Variable: qsec --------------------------------
#>
#> ------------------------------ Summary Statistics ------------------------------
#>
#> -------------------------------- Variable: qsec --------------------------------
#>
#> Univariate Analysis
#>
#> N 32.00 Variance 3.19
#> Missing 0.00 Std Deviation 1.79
#> Mean 17.85 Range 8.40
#> Median 17.71 Interquartile Range 2.01
#> Mode 17.02 Uncorrected SS 10293.48
#> Trimmed Mean 17.79 Corrected SS 98.99
#> Skewness 0.41 Coeff Variation 10.01
#> Kurtosis 0.86 Std Error Mean 0.32
#>
#> Quantiles
#>
#> Quantile Value
#>
#> Max 22.90
#> 99% 22.07
#> 95% 20.10
#> 90% 19.99
#> Q3 18.90
#> Median 17.71
#> Q1 16.89
#> 10% 15.53
#> 5% 15.05
#> 1% 14.53
#> Min 14.50
#>
#> Extreme Values
#>
#> Low High
#>
#> Obs Value Obs Value
#> 29 14.5 9 22.9
#> 31 14.6 6 20.22
#> 24 15.41 21 20.01
#> 30 15.5 8 20
#> 7 15.84 20 19.9
#>
#>
#>
#> NULL
#>
#>
#> ---------------------------- Frequency Distribution ----------------------------
#>
#> Variable: qsec
#> |-------------------------------------------------------------------------|
#> | Bins | Frequency | Cum Frequency | Percent | Cum Percent |
#> |-------------------------------------------------------------------------|
#> | 14.5 - 16.2 | 5 | 5 | 15.62 | 15.62 |
#> |-------------------------------------------------------------------------|
#> | 16.2 - 17.9 | 12 | 17 | 37.5 | 53.12 |
#> |-------------------------------------------------------------------------|
#> | 17.9 - 19.5 | 10 | 27 | 31.25 | 84.38 |
#> |-------------------------------------------------------------------------|
#> | 19.5 - 21.2 | 4 | 31 | 12.5 | 96.88 |
#> |-------------------------------------------------------------------------|
#> | 21.2 - 22.9 | 1 | 32 | 3.12 | 100 |
#> |-------------------------------------------------------------------------|
#> | Total | 32 | - | 100.00 | - |
#> |-------------------------------------------------------------------------|
#>
#>
# multiple columns
ds_auto_summary_stats(mtcarz, disp, hp)
#> -------------------------------- Variable: disp --------------------------------
#>
#> ------------------------------ Summary Statistics ------------------------------
#>
#> -------------------------------- Variable: disp --------------------------------
#>
#> Univariate Analysis
#>
#> N 32.00 Variance 15360.80
#> Missing 0.00 Std Deviation 123.94
#> Mean 230.72 Range 400.90
#> Median 196.30 Interquartile Range 205.18
#> Mode 275.80 Uncorrected SS 2179627.47
#> Trimmed Mean 228.00 Corrected SS 476184.79
#> Skewness 0.42 Coeff Variation 53.72
#> Kurtosis -1.07 Std Error Mean 21.91
#>
#> Quantiles
#>
#> Quantile Value
#>
#> Max 472.00
#> 99% 468.28
#> 95% 449.00
#> 90% 396.00
#> Q3 326.00
#> Median 196.30
#> Q1 120.83
#> 10% 80.61
#> 5% 77.35
#> 1% 72.53
#> Min 71.10
#>
#> Extreme Values
#>
#> Low High
#>
#> Obs Value Obs Value
#> 20 71.1 15 472
#> 19 75.7 16 460
#> 18 78.7 17 440
#> 26 79 25 400
#> 28 95.1 5 360
#>
#>
#>
#> NULL
#>
#>
#> ---------------------------- Frequency Distribution ----------------------------
#>
#> Variable: disp
#> |---------------------------------------------------------------------------|
#> | Bins | Frequency | Cum Frequency | Percent | Cum Percent |
#> |---------------------------------------------------------------------------|
#> | 71.1 - 151.3 | 12 | 12 | 37.5 | 37.5 |
#> |---------------------------------------------------------------------------|
#> | 151.3 - 231.5 | 5 | 17 | 15.62 | 53.12 |
#> |---------------------------------------------------------------------------|
#> | 231.5 - 311.6 | 6 | 23 | 18.75 | 71.88 |
#> |---------------------------------------------------------------------------|
#> | 311.6 - 391.8 | 5 | 28 | 15.62 | 87.5 |
#> |---------------------------------------------------------------------------|
#> | 391.8 - 472 | 4 | 32 | 12.5 | 100 |
#> |---------------------------------------------------------------------------|
#> | Total | 32 | - | 100.00 | - |
#> |---------------------------------------------------------------------------|
#>
#>
#> --------------------------------- Variable: hp ---------------------------------
#>
#> ------------------------------ Summary Statistics ------------------------------
#>
#> --------------------------------- Variable: hp ---------------------------------
#>
#> Univariate Analysis
#>
#> N 32.00 Variance 4700.87
#> Missing 0.00 Std Deviation 68.56
#> Mean 146.69 Range 283.00
#> Median 123.00 Interquartile Range 83.50
#> Mode 110.00 Uncorrected SS 834278.00
#> Trimmed Mean 143.57 Corrected SS 145726.88
#> Skewness 0.80 Coeff Variation 46.74
#> Kurtosis 0.28 Std Error Mean 12.12
#>
#> Quantiles
#>
#> Quantile Value
#>
#> Max 335.00
#> 99% 312.99
#> 95% 253.55
#> 90% 243.50
#> Q3 180.00
#> Median 123.00
#> Q1 96.50
#> 10% 66.00
#> 5% 63.65
#> 1% 55.10
#> Min 52.00
#>
#> Extreme Values
#>
#> Low High
#>
#> Obs Value Obs Value
#> 19 52 31 335
#> 8 62 29 264
#> 20 65 7 245
#> 18 66 24 245
#> 26 66 17 230
#>
#>
#>
#> NULL
#>
#>
#> ---------------------------- Frequency Distribution ----------------------------
#>
#> Variable: hp
#> |-------------------------------------------------------------------------|
#> | Bins | Frequency | Cum Frequency | Percent | Cum Percent |
#> |-------------------------------------------------------------------------|
#> | 52 - 108.6 | 10 | 10 | 31.25 | 31.25 |
#> |-------------------------------------------------------------------------|
#> | 108.6 - 165.2 | 9 | 19 | 28.12 | 59.38 |
#> |-------------------------------------------------------------------------|
#> | 165.2 - 221.8 | 8 | 27 | 25 | 84.38 |
#> |-------------------------------------------------------------------------|
#> | 221.8 - 278.4 | 4 | 31 | 12.5 | 96.88 |
#> |-------------------------------------------------------------------------|
#> | 278.4 - 335 | 1 | 32 | 3.12 | 100 |
#> |-------------------------------------------------------------------------|
#> | Total | 32 | - | 100.00 | - |
#> |-------------------------------------------------------------------------|
#>
#>