# import dependencies
import pandas as pd
# pandas_profiling finds essential values, provides statistics, and creates correlation matrixes
# https://github.com/pandas-profiling/pandas-profiling
import pandas_profiling
# import csv saved from the numeric_survey function
surveyDF = pd.read_csv('../data/survey04172018.csv')
surveyDF.head()
| work_zip | home_zip | gender_values | age | race_values | income_values | days_last_values | time_between_values | products_values | spend_values | max_spend_values | how_find_values | review_values | price | convenient | atmosphere | amenities | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 92614 | 92614 | 1 | 38.0 | 1.0 | 1.0 | 1.0 | 3.0 | 0.0 | 5.0 | 5.0 | 3.0 | 1.0 | 4 | 4 | 4 | 1 |
| 1 | 92660 | 92677 | 1 | 34.0 | 4.0 | 5.0 | 6.0 | 7.0 | 0.0 | 5.0 | 7.0 | 2.0 | 2.0 | 5 | 3 | 3 | 1 |
| 2 | 92612 | 92602 | 0 | 35.0 | 4.0 | 4.0 | 0.0 | 7.0 | 1.0 | 5.0 | 0.0 | 3.0 | 2.0 | 5 | 5 | 4 | 4 |
| 3 | 92620 | 92780 | 1 | 35.0 | 1.0 | 4.0 | 1.0 | 3.0 | 1.0 | 5.0 | 6.0 | 3.0 | 3.0 | 3 | 5 | 4 | 4 |
| 4 | 97205 | 97205 | 1 | 38.0 | 4.0 | 4.0 | 1.0 | 6.0 | 0.0 | 5.0 | 5.0 | 4.0 | 3.0 | 4 | 2 | 3 | 2 |
# run the pandas profiling report
pandas_profiling.ProfileReport(surveyDF)
Dataset info
| Number of variables | 17 |
|---|---|
| Number of observations | 104 |
| Total Missing (%) | 0.0% |
| Total size in memory | 13.9 KiB |
| Average record size in memory | 136.8 B |
Variables types
| Numeric | 15 |
|---|---|
| Categorical | 0 |
| Boolean | 2 |
| Date | 0 |
| Text (Unique) | 0 |
| Rejected | 0 |
| Unsupported | 0 |
Warnings
age has 4 / 3.8% zeros Zerosdays_last_values has 3 / 2.9% zeros Zeroshow_find_values has 17 / 16.3% zeros Zerosincome_values has 8 / 7.7% zeros Zerosmax_spend_values has 4 / 3.8% zeros Zerosrace_values has 3 / 2.9% zeros Zerosspend_values has 10 / 9.6% zeros Zerostime_between_values has 15 / 14.4% zeros Zerosage
Numeric
| Distinct count | 27 |
|---|---|
| Unique (%) | 26.0% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 31.163 |
|---|---|
| Minimum | 0 |
| Maximum | 54 |
| Zeros (%) | 3.8% |
Quantile statistics
| Minimum | 0 |
|---|---|
| 5-th percentile | 21 |
| Q1 | 27 |
| Median | 32 |
| Q3 | 36 |
| 95-th percentile | 44.4 |
| Maximum | 54 |
| Range | 54 |
| Interquartile range | 9 |
Descriptive statistics
| Standard deviation | 9.019 |
|---|---|
| Coef of variation | 0.28941 |
| Kurtosis | 3.9753 |
| Mean | 31.163 |
| MAD | 6.2408 |
| Skewness | -1.2281 |
| Sum | 3241 |
| Variance | 81.342 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 35.0 | 10 | 9.6% |
|
| 32.0 | 10 | 9.6% |
|
| 38.0 | 7 | 6.7% |
|
| 33.0 | 6 | 5.8% |
|
| 30.0 | 6 | 5.8% |
|
| 39.0 | 6 | 5.8% |
|
| 28.0 | 6 | 5.8% |
|
| 31.0 | 5 | 4.8% |
|
| 0.0 | 4 | 3.8% |
|
| 24.0 | 4 | 3.8% |
|
| Other values (17) | 40 | 38.5% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 0.0 | 4 | 3.8% |
|
| 21.0 | 3 | 2.9% |
|
| 22.0 | 4 | 3.8% |
|
| 23.0 | 4 | 3.8% |
|
| 24.0 | 4 | 3.8% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 45.0 | 1 | 1.0% |
|
| 46.0 | 2 | 1.9% |
|
| 48.0 | 1 | 1.0% |
|
| 50.0 | 1 | 1.0% |
|
| 54.0 | 1 | 1.0% |
|
amenities
Numeric
| Distinct count | 5 |
|---|---|
| Unique (%) | 4.8% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 2.3269 |
|---|---|
| Minimum | 1 |
| Maximum | 5 |
| Zeros (%) | 0.0% |
Quantile statistics
| Minimum | 1 |
|---|---|
| 5-th percentile | 1 |
| Q1 | 1 |
| Median | 2 |
| Q3 | 3 |
| 95-th percentile | 5 |
| Maximum | 5 |
| Range | 4 |
| Interquartile range | 2 |
Descriptive statistics
| Standard deviation | 1.303 |
|---|---|
| Coef of variation | 0.55998 |
| Kurtosis | -0.8036 |
| Mean | 2.3269 |
| MAD | 1.1206 |
| Skewness | 0.60333 |
| Sum | 242 |
| Variance | 1.6979 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 1 | 38 | 36.5% |
|
| 2 | 24 | 23.1% |
|
| 3 | 20 | 19.2% |
|
| 4 | 14 | 13.5% |
|
| 5 | 8 | 7.7% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 1 | 38 | 36.5% |
|
| 2 | 24 | 23.1% |
|
| 3 | 20 | 19.2% |
|
| 4 | 14 | 13.5% |
|
| 5 | 8 | 7.7% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 1 | 38 | 36.5% |
|
| 2 | 24 | 23.1% |
|
| 3 | 20 | 19.2% |
|
| 4 | 14 | 13.5% |
|
| 5 | 8 | 7.7% |
|
atmosphere
Numeric
| Distinct count | 5 |
|---|---|
| Unique (%) | 4.8% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 3.0769 |
|---|---|
| Minimum | 1 |
| Maximum | 5 |
| Zeros (%) | 0.0% |
Quantile statistics
| Minimum | 1 |
|---|---|
| 5-th percentile | 1 |
| Q1 | 2 |
| Median | 3 |
| Q3 | 4 |
| 95-th percentile | 5 |
| Maximum | 5 |
| Range | 4 |
| Interquartile range | 2 |
Descriptive statistics
| Standard deviation | 1.1962 |
|---|---|
| Coef of variation | 0.38877 |
| Kurtosis | -0.81443 |
| Mean | 3.0769 |
| MAD | 0.95858 |
| Skewness | -0.18541 |
| Sum | 320 |
| Variance | 1.4309 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 3 | 31 | 29.8% |
|
| 4 | 29 | 27.9% |
|
| 2 | 19 | 18.3% |
|
| 1 | 13 | 12.5% |
|
| 5 | 12 | 11.5% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 1 | 13 | 12.5% |
|
| 2 | 19 | 18.3% |
|
| 3 | 31 | 29.8% |
|
| 4 | 29 | 27.9% |
|
| 5 | 12 | 11.5% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 1 | 13 | 12.5% |
|
| 2 | 19 | 18.3% |
|
| 3 | 31 | 29.8% |
|
| 4 | 29 | 27.9% |
|
| 5 | 12 | 11.5% |
|
convenient
Numeric
| Distinct count | 5 |
|---|---|
| Unique (%) | 4.8% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 4.0673 |
|---|---|
| Minimum | 1 |
| Maximum | 5 |
| Zeros (%) | 0.0% |
Quantile statistics
| Minimum | 1 |
|---|---|
| 5-th percentile | 1.15 |
| Q1 | 4 |
| Median | 4 |
| Q3 | 5 |
| 95-th percentile | 5 |
| Maximum | 5 |
| Range | 4 |
| Interquartile range | 1 |
Descriptive statistics
| Standard deviation | 1.1681 |
|---|---|
| Coef of variation | 0.28718 |
| Kurtosis | 0.83041 |
| Mean | 4.0673 |
| MAD | 0.87888 |
| Skewness | -1.2883 |
| Sum | 423 |
| Variance | 1.3644 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 5 | 49 | 47.1% |
|
| 4 | 32 | 30.8% |
|
| 3 | 10 | 9.6% |
|
| 2 | 7 | 6.7% |
|
| 1 | 6 | 5.8% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 1 | 6 | 5.8% |
|
| 2 | 7 | 6.7% |
|
| 3 | 10 | 9.6% |
|
| 4 | 32 | 30.8% |
|
| 5 | 49 | 47.1% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 1 | 6 | 5.8% |
|
| 2 | 7 | 6.7% |
|
| 3 | 10 | 9.6% |
|
| 4 | 32 | 30.8% |
|
| 5 | 49 | 47.1% |
|
days_last_values
Numeric
| Distinct count | 8 |
|---|---|
| Unique (%) | 7.7% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 2.7308 |
|---|---|
| Minimum | 0 |
| Maximum | 7 |
| Zeros (%) | 2.9% |
Quantile statistics
| Minimum | 0 |
|---|---|
| 5-th percentile | 1 |
| Q1 | 1 |
| Median | 2 |
| Q3 | 4 |
| 95-th percentile | 7 |
| Maximum | 7 |
| Range | 7 |
| Interquartile range | 3 |
Descriptive statistics
| Standard deviation | 1.8074 |
|---|---|
| Coef of variation | 0.66186 |
| Kurtosis | 0.096134 |
| Mean | 2.7308 |
| MAD | 1.4512 |
| Skewness | 0.87487 |
| Sum | 284 |
| Variance | 3.2666 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 1.0 | 30 | 28.8% |
|
| 3.0 | 21 | 20.2% |
|
| 2.0 | 21 | 20.2% |
|
| 4.0 | 13 | 12.5% |
|
| 7.0 | 7 | 6.7% |
|
| 5.0 | 6 | 5.8% |
|
| 0.0 | 3 | 2.9% |
|
| 6.0 | 3 | 2.9% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 0.0 | 3 | 2.9% |
|
| 1.0 | 30 | 28.8% |
|
| 2.0 | 21 | 20.2% |
|
| 3.0 | 21 | 20.2% |
|
| 4.0 | 13 | 12.5% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 3.0 | 21 | 20.2% |
|
| 4.0 | 13 | 12.5% |
|
| 5.0 | 6 | 5.8% |
|
| 6.0 | 3 | 2.9% |
|
| 7.0 | 7 | 6.7% |
|
gender_values
Boolean
| Distinct count | 2 |
|---|---|
| Unique (%) | 1.9% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Mean | 0.91346 |
|---|
| 1 |
95
|
|---|---|
| 0 |
|
| Value | Count | Frequency (%) | |
| 1 | 95 | 91.3% |
|
| 0 | 9 | 8.7% |
|
home_zip
Numeric
| Distinct count | 80 |
|---|---|
| Unique (%) | 76.9% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 88181 |
|---|---|
| Minimum | 1801 |
| Maximum | 98065 |
| Zeros (%) | 0.0% |
Quantile statistics
| Minimum | 1801 |
|---|---|
| 5-th percentile | 37475 |
| Q1 | 91769 |
| Median | 92627 |
| Q3 | 92805 |
| 95-th percentile | 94576 |
| Maximum | 98065 |
| Range | 96264 |
| Interquartile range | 1036 |
Descriptive statistics
| Standard deviation | 18362 |
|---|---|
| Coef of variation | 0.20823 |
| Kurtosis | 13.919 |
| Mean | 88181 |
| MAD | 8442.4 |
| Skewness | -3.9127 |
| Sum | 9170835 |
| Variance | 337170000 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 92618 | 4 | 3.8% |
|
| 92627 | 4 | 3.8% |
|
| 92602 | 3 | 2.9% |
|
| 92782 | 3 | 2.9% |
|
| 92780 | 2 | 1.9% |
|
| 92887 | 2 | 1.9% |
|
| 92123 | 2 | 1.9% |
|
| 91344 | 2 | 1.9% |
|
| 91748 | 2 | 1.9% |
|
| 92647 | 2 | 1.9% |
|
| Other values (70) | 78 | 75.0% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 1801 | 1 | 1.0% |
|
| 8125 | 1 | 1.0% |
|
| 10028 | 1 | 1.0% |
|
| 20816 | 1 | 1.0% |
|
| 21108 | 1 | 1.0% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 94609 | 1 | 1.0% |
|
| 94610 | 1 | 1.0% |
|
| 95127 | 1 | 1.0% |
|
| 97205 | 1 | 1.0% |
|
| 98065 | 1 | 1.0% |
|
how_find_values
Numeric
| Distinct count | 5 |
|---|---|
| Unique (%) | 4.8% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 1.6923 |
|---|---|
| Minimum | 0 |
| Maximum | 4 |
| Zeros (%) | 16.3% |
Quantile statistics
| Minimum | 0 |
|---|---|
| 5-th percentile | 0 |
| Q1 | 1 |
| Median | 2 |
| Q3 | 2 |
| 95-th percentile | 3 |
| Maximum | 4 |
| Range | 4 |
| Interquartile range | 1 |
Descriptive statistics
| Standard deviation | 1.071 |
|---|---|
| Coef of variation | 0.63289 |
| Kurtosis | -0.78118 |
| Mean | 1.6923 |
| MAD | 0.89941 |
| Skewness | -0.031466 |
| Sum | 176 |
| Variance | 1.1471 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 2.0 | 36 | 34.6% |
|
| 1.0 | 26 | 25.0% |
|
| 3.0 | 22 | 21.2% |
|
| 0.0 | 17 | 16.3% |
|
| 4.0 | 3 | 2.9% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 0.0 | 17 | 16.3% |
|
| 1.0 | 26 | 25.0% |
|
| 2.0 | 36 | 34.6% |
|
| 3.0 | 22 | 21.2% |
|
| 4.0 | 3 | 2.9% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 0.0 | 17 | 16.3% |
|
| 1.0 | 26 | 25.0% |
|
| 2.0 | 36 | 34.6% |
|
| 3.0 | 22 | 21.2% |
|
| 4.0 | 3 | 2.9% |
|
income_values
Numeric
| Distinct count | 9 |
|---|---|
| Unique (%) | 8.7% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 4.2692 |
|---|---|
| Minimum | 0 |
| Maximum | 8 |
| Zeros (%) | 7.7% |
Quantile statistics
| Minimum | 0 |
|---|---|
| 5-th percentile | 0 |
| Q1 | 3 |
| Median | 5 |
| Q3 | 6 |
| 95-th percentile | 8 |
| Maximum | 8 |
| Range | 8 |
| Interquartile range | 3 |
Descriptive statistics
| Standard deviation | 2.2822 |
|---|---|
| Coef of variation | 0.53457 |
| Kurtosis | -0.70631 |
| Mean | 4.2692 |
| MAD | 1.841 |
| Skewness | -0.34922 |
| Sum | 444 |
| Variance | 5.2084 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 4.0 | 20 | 19.2% |
|
| 5.0 | 20 | 19.2% |
|
| 6.0 | 17 | 16.3% |
|
| 1.0 | 12 | 11.5% |
|
| 0.0 | 8 | 7.7% |
|
| 7.0 | 8 | 7.7% |
|
| 8.0 | 8 | 7.7% |
|
| 3.0 | 8 | 7.7% |
|
| 2.0 | 3 | 2.9% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 0.0 | 8 | 7.7% |
|
| 1.0 | 12 | 11.5% |
|
| 2.0 | 3 | 2.9% |
|
| 3.0 | 8 | 7.7% |
|
| 4.0 | 20 | 19.2% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 4.0 | 20 | 19.2% |
|
| 5.0 | 20 | 19.2% |
|
| 6.0 | 17 | 16.3% |
|
| 7.0 | 8 | 7.7% |
|
| 8.0 | 8 | 7.7% |
|
max_spend_values
Numeric
| Distinct count | 8 |
|---|---|
| Unique (%) | 7.7% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 3.4038 |
|---|---|
| Minimum | 0 |
| Maximum | 7 |
| Zeros (%) | 3.8% |
Quantile statistics
| Minimum | 0 |
|---|---|
| 5-th percentile | 1 |
| Q1 | 2 |
| Median | 3 |
| Q3 | 4 |
| 95-th percentile | 7 |
| Maximum | 7 |
| Range | 7 |
| Interquartile range | 2 |
Descriptive statistics
| Standard deviation | 1.6867 |
|---|---|
| Coef of variation | 0.49553 |
| Kurtosis | -0.094944 |
| Mean | 3.4038 |
| MAD | 1.3317 |
| Skewness | 0.46645 |
| Sum | 354 |
| Variance | 2.845 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 3.0 | 34 | 32.7% |
|
| 2.0 | 23 | 22.1% |
|
| 4.0 | 15 | 14.4% |
|
| 5.0 | 9 | 8.7% |
|
| 6.0 | 8 | 7.7% |
|
| 7.0 | 7 | 6.7% |
|
| 1.0 | 4 | 3.8% |
|
| 0.0 | 4 | 3.8% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 0.0 | 4 | 3.8% |
|
| 1.0 | 4 | 3.8% |
|
| 2.0 | 23 | 22.1% |
|
| 3.0 | 34 | 32.7% |
|
| 4.0 | 15 | 14.4% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 3.0 | 34 | 32.7% |
|
| 4.0 | 15 | 14.4% |
|
| 5.0 | 9 | 8.7% |
|
| 6.0 | 8 | 7.7% |
|
| 7.0 | 7 | 6.7% |
|
price
Numeric
| Distinct count | 5 |
|---|---|
| Unique (%) | 4.8% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 3.8269 |
|---|---|
| Minimum | 1 |
| Maximum | 5 |
| Zeros (%) | 0.0% |
Quantile statistics
| Minimum | 1 |
|---|---|
| 5-th percentile | 2 |
| Q1 | 3 |
| Median | 4 |
| Q3 | 5 |
| 95-th percentile | 5 |
| Maximum | 5 |
| Range | 4 |
| Interquartile range | 2 |
Descriptive statistics
| Standard deviation | 1.0282 |
|---|---|
| Coef of variation | 0.26867 |
| Kurtosis | -0.24737 |
| Mean | 3.8269 |
| MAD | 0.82581 |
| Skewness | -0.62773 |
| Sum | 398 |
| Variance | 1.0571 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 4 | 38 | 36.5% |
|
| 5 | 31 | 29.8% |
|
| 3 | 23 | 22.1% |
|
| 2 | 10 | 9.6% |
|
| 1 | 2 | 1.9% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 1 | 2 | 1.9% |
|
| 2 | 10 | 9.6% |
|
| 3 | 23 | 22.1% |
|
| 4 | 38 | 36.5% |
|
| 5 | 31 | 29.8% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 1 | 2 | 1.9% |
|
| 2 | 10 | 9.6% |
|
| 3 | 23 | 22.1% |
|
| 4 | 38 | 36.5% |
|
| 5 | 31 | 29.8% |
|
products_values
Boolean
| Distinct count | 2 |
|---|---|
| Unique (%) | 1.9% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Mean | 0.16346 |
|---|
| 0.0 |
87
|
|---|---|
| 1.0 |
|
| Value | Count | Frequency (%) | |
| 0.0 | 87 | 83.7% |
|
| 1.0 | 17 | 16.3% |
|
race_values
Numeric
| Distinct count | 6 |
|---|---|
| Unique (%) | 5.8% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 2.3269 |
|---|---|
| Minimum | 0 |
| Maximum | 5 |
| Zeros (%) | 2.9% |
Quantile statistics
| Minimum | 0 |
|---|---|
| 5-th percentile | 1 |
| Q1 | 1 |
| Median | 1 |
| Q3 | 4 |
| 95-th percentile | 4 |
| Maximum | 5 |
| Range | 5 |
| Interquartile range | 3 |
Descriptive statistics
| Standard deviation | 1.5229 |
|---|---|
| Coef of variation | 0.65448 |
| Kurtosis | -1.7472 |
| Mean | 2.3269 |
| MAD | 1.4675 |
| Skewness | 0.21882 |
| Sum | 242 |
| Variance | 2.3193 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 1.0 | 52 | 50.0% |
|
| 4.0 | 38 | 36.5% |
|
| 3.0 | 7 | 6.7% |
|
| 5.0 | 3 | 2.9% |
|
| 0.0 | 3 | 2.9% |
|
| 2.0 | 1 | 1.0% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 0.0 | 3 | 2.9% |
|
| 1.0 | 52 | 50.0% |
|
| 2.0 | 1 | 1.0% |
|
| 3.0 | 7 | 6.7% |
|
| 4.0 | 38 | 36.5% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 1.0 | 52 | 50.0% |
|
| 2.0 | 1 | 1.0% |
|
| 3.0 | 7 | 6.7% |
|
| 4.0 | 38 | 36.5% |
|
| 5.0 | 3 | 2.9% |
|
review_values
Numeric
| Distinct count | 4 |
|---|---|
| Unique (%) | 3.8% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 2.0577 |
|---|---|
| Minimum | 0 |
| Maximum | 3 |
| Zeros (%) | 1.0% |
Quantile statistics
| Minimum | 0 |
|---|---|
| 5-th percentile | 1 |
| Q1 | 2 |
| Median | 2 |
| Q3 | 2 |
| 95-th percentile | 3 |
| Maximum | 3 |
| Range | 3 |
| Interquartile range | 0 |
Descriptive statistics
| Standard deviation | 0.60462 |
|---|---|
| Coef of variation | 0.29384 |
| Kurtosis | 0.81903 |
| Mean | 2.0577 |
| MAD | 0.38055 |
| Skewness | -0.29276 |
| Sum | 214 |
| Variance | 0.36557 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 2.0 | 69 | 66.3% |
|
| 3.0 | 21 | 20.2% |
|
| 1.0 | 13 | 12.5% |
|
| 0.0 | 1 | 1.0% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 0.0 | 1 | 1.0% |
|
| 1.0 | 13 | 12.5% |
|
| 2.0 | 69 | 66.3% |
|
| 3.0 | 21 | 20.2% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 0.0 | 1 | 1.0% |
|
| 1.0 | 13 | 12.5% |
|
| 2.0 | 69 | 66.3% |
|
| 3.0 | 21 | 20.2% |
|
spend_values
Numeric
| Distinct count | 6 |
|---|---|
| Unique (%) | 5.8% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 2.6346 |
|---|---|
| Minimum | 0 |
| Maximum | 5 |
| Zeros (%) | 9.6% |
Quantile statistics
| Minimum | 0 |
|---|---|
| 5-th percentile | 0 |
| Q1 | 2 |
| Median | 3 |
| Q3 | 3.25 |
| 95-th percentile | 5 |
| Maximum | 5 |
| Range | 5 |
| Interquartile range | 1.25 |
Descriptive statistics
| Standard deviation | 1.4485 |
|---|---|
| Coef of variation | 0.5498 |
| Kurtosis | -0.59703 |
| Mean | 2.6346 |
| MAD | 1.1749 |
| Skewness | -0.019643 |
| Sum | 274 |
| Variance | 2.0982 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 2.0 | 29 | 27.9% |
|
| 3.0 | 29 | 27.9% |
|
| 5.0 | 15 | 14.4% |
|
| 4.0 | 11 | 10.6% |
|
| 1.0 | 10 | 9.6% |
|
| 0.0 | 10 | 9.6% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 0.0 | 10 | 9.6% |
|
| 1.0 | 10 | 9.6% |
|
| 2.0 | 29 | 27.9% |
|
| 3.0 | 29 | 27.9% |
|
| 4.0 | 11 | 10.6% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 1.0 | 10 | 9.6% |
|
| 2.0 | 29 | 27.9% |
|
| 3.0 | 29 | 27.9% |
|
| 4.0 | 11 | 10.6% |
|
| 5.0 | 15 | 14.4% |
|
time_between_values
Numeric
| Distinct count | 7 |
|---|---|
| Unique (%) | 6.7% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 3.5192 |
|---|---|
| Minimum | 0 |
| Maximum | 7 |
| Zeros (%) | 14.4% |
Quantile statistics
| Minimum | 0 |
|---|---|
| 5-th percentile | 0 |
| Q1 | 2 |
| Median | 3 |
| Q3 | 6 |
| 95-th percentile | 7 |
| Maximum | 7 |
| Range | 7 |
| Interquartile range | 4 |
Descriptive statistics
| Standard deviation | 2.2076 |
|---|---|
| Coef of variation | 0.62729 |
| Kurtosis | -0.99057 |
| Mean | 3.5192 |
| MAD | 1.8277 |
| Skewness | -0.0041038 |
| Sum | 366 |
| Variance | 4.8734 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 4.0 | 20 | 19.2% |
|
| 3.0 | 20 | 19.2% |
|
| 6.0 | 19 | 18.3% |
|
| 2.0 | 16 | 15.4% |
|
| 0.0 | 15 | 14.4% |
|
| 7.0 | 11 | 10.6% |
|
| 1.0 | 3 | 2.9% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 0.0 | 15 | 14.4% |
|
| 1.0 | 3 | 2.9% |
|
| 2.0 | 16 | 15.4% |
|
| 3.0 | 20 | 19.2% |
|
| 4.0 | 20 | 19.2% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 2.0 | 16 | 15.4% |
|
| 3.0 | 20 | 19.2% |
|
| 4.0 | 20 | 19.2% |
|
| 6.0 | 19 | 18.3% |
|
| 7.0 | 11 | 10.6% |
|
work_zip
Numeric
| Distinct count | 75 |
|---|---|
| Unique (%) | 72.1% |
| Missing (%) | 0.0% |
| Missing (n) | 0 |
| Infinite (%) | 0.0% |
| Infinite (n) | 0 |
| Mean | 88987 |
|---|---|
| Minimum | 1730 |
| Maximum | 98065 |
| Zeros (%) | 0.0% |
Quantile statistics
| Minimum | 1730 |
|---|---|
| 5-th percentile | 90010 |
| Q1 | 91910 |
| Median | 92648 |
| Q3 | 92821 |
| 95-th percentile | 94695 |
| Maximum | 98065 |
| Range | 96335 |
| Interquartile range | 911 |
Descriptive statistics
| Standard deviation | 16580 |
|---|---|
| Coef of variation | 0.18632 |
| Kurtosis | 17.789 |
| Mean | 88987 |
| MAD | 6980.8 |
| Skewness | -4.35 |
| Sum | 9254619 |
| Variance | 274910000 |
| Memory size | 912.0 B |
| Value | Count | Frequency (%) | |
| 92660 | 10 | 9.6% |
|
| 92618 | 7 | 6.7% |
|
| 92612 | 4 | 3.8% |
|
| 92606 | 3 | 2.9% |
|
| 92656 | 3 | 2.9% |
|
| 92821 | 3 | 2.9% |
|
| 94080 | 2 | 1.9% |
|
| 93550 | 2 | 1.9% |
|
| 92614 | 2 | 1.9% |
|
| 91910 | 2 | 1.9% |
|
| Other values (65) | 66 | 63.5% |
|
Minimum 5 values
| Value | Count | Frequency (%) | |
| 1730 | 1 | 1.0% |
|
| 10019 | 1 | 1.0% |
|
| 20815 | 1 | 1.0% |
|
| 21108 | 1 | 1.0% |
|
| 28262 | 1 | 1.0% |
|
Maximum 5 values
| Value | Count | Frequency (%) | |
| 94720 | 1 | 1.0% |
|
| 95054 | 1 | 1.0% |
|
| 97205 | 1 | 1.0% |
|
| 98052 | 1 | 1.0% |
|
| 98065 | 1 | 1.0% |
|
| work_zip | home_zip | gender_values | age | race_values | income_values | days_last_values | time_between_values | products_values | spend_values | max_spend_values | how_find_values | review_values | price | convenient | atmosphere | amenities | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 92614 | 92614 | 1 | 38.0 | 1.0 | 1.0 | 1.0 | 3.0 | 0.0 | 5.0 | 5.0 | 3.0 | 1.0 | 4 | 4 | 4 | 1 |
| 1 | 92660 | 92677 | 1 | 34.0 | 4.0 | 5.0 | 6.0 | 7.0 | 0.0 | 5.0 | 7.0 | 2.0 | 2.0 | 5 | 3 | 3 | 1 |
| 2 | 92612 | 92602 | 0 | 35.0 | 4.0 | 4.0 | 0.0 | 7.0 | 1.0 | 5.0 | 0.0 | 3.0 | 2.0 | 5 | 5 | 4 | 4 |
| 3 | 92620 | 92780 | 1 | 35.0 | 1.0 | 4.0 | 1.0 | 3.0 | 1.0 | 5.0 | 6.0 | 3.0 | 3.0 | 3 | 5 | 4 | 4 |
| 4 | 97205 | 97205 | 1 | 38.0 | 4.0 | 4.0 | 1.0 | 6.0 | 0.0 | 5.0 | 5.0 | 4.0 | 3.0 | 4 | 2 | 3 | 2 |