This article directory:
1.None and np.nan difference?
2.pandas null value introduced;
2.1excel manufacturing data table;
2.2 read transactions;
2.3 describes the missing values, causes, classification, attributes, forms:
3. artificially null
4. null operation
The difference 1.None and np.nan?
2.pandas null operations:
Involves functions: the any, All; ISNULL (), NotNull (), dropna (), fillna (), ISNA ()
https://www.douban.com/note/714022352/
2.1excel manufacturing data
2.2 to read data
The following operations are opened in jupyter notebook, a terminal open command: jupyter Notebook
2.3 missing values introduced, causes, classification, attributes, forms:
1. The value of the missing data is missing;
2. Reason:
mechanical reasons: data collection or storage data fails due to missing;
man-made causes: people's subjective mistakes, historical confinement or missing data intended to conceal the cause of the market survey respondents who declined to give answers to questions, or answer the question invalid data entry personnel mistakes missing recorded data;
3 Category:
missing completely at random: random missing data, missing data is not dependent on any incomplete or complete variable variable;
missing data: missing data is not completely random, i.e., the class data deletion completely dependent on other variables;
full non-missing data: missing data depends on the variable itself incomplete;
4. attribute:
single missing value: the missing values are all of the same attribute;
any missing: missing values belonging to different properties;
monotone missing: in the time series data and the like, may be present with the absence of time;
5. form: N one, np.nan, NaT;
