df-stat.py

dfSelected.printSchema()     # 스키마를 확인합니다.
dfSelected.describe().show() # 통계 정보를 확인합니다. PySpark 에서는 `show` 대신 `toPandas` 를 활용할 수 있습니다.

# printSchema() 의 출력 결과
root
 |-- id: integer (nullable = true)
 |-- year_birth: integer (nullable = true)
 |-- education: string (nullable = true)
 |-- count_kid: integer (nullable = true)
 |-- count_teen: integer (nullable = true)
 |-- date_customer: string (nullable = true)
 |-- days_last_login: integer (nullable = true)

# describe().show() 의 출력 결과
+-------+------------------+------------------+---------+-------------------+------------------+-------------+-----------------+
|summary|                id|        year_birth|education|          count_kid|         count_kid|date_customer|  days_last_login|
+-------+------------------+------------------+---------+-------------------+------------------+-------------+-----------------+
|  count|              2240|              2240|     2240|               2240|              2240|         2240|             2240|
|   mean| 5592.159821428571|1968.8058035714287|     null|0.44419642857142855|           0.50625|         null|        49.109375|
| stddev|3246.6621975643416|11.984069456885827|     null| 0.5383980977345935|0.5445382307698761|         null|28.96245280837821|
|    min|                 0|              1893| 2n Cycle|                  0|                 0|   01-01-2013|                0|
|    max|             11191|              1996|      PhD|                  2|                 2|   31-12-2013|               99|
+-------+------------------+------------------+---------+-------------------+------------------+-------------+-----------------+