Survey#

class tangles.convenience.Survey(data: DataFrame)#

Objects of this class represent survey data and provide functions to prepare, clean and subset survey data.

This class manages a pandas dataframe and a data structure containing information about the variables. It makes sure that the information in both of these objects stays synchronized.

Parameters#

datapandas.DataFrame: A dataframe containing the survey data.

Properties

`num_questions`	Number of questions (or variables)
`num_respondents`	Number of respondents
`shape`	The shape of the data

Methods

`__getitem__()`	Retrieve a data element/slice/subset/
`check_variables()`	Check if we can conveniently use the information in this survey for a tangle analysis
`complete_rows()`	Find out which rows are complete
`copy()`	Create a copy of this Survey
`count_number_of_unique_answers()`	Count the number of unique answers for selected columns
`count_valid_answers_per_respondent()`	Count the number of valid answers for each respondent
`guess_variable_types()`	Guess missing variable types from data
`guess_variable_value_lists()`	Guess missing variable value lists from data
`interpret_column_selection()`	Interpret different ways to select a subset of columns (or variables)
`load()`	Load a `Survey` from files
`replace_variable_value_labels()`	Replace variable value labels according to the dictionary mapping
`replace_variable_values()`	Replace the values found in the selected columns by different values
`save()`	Save this survey to a folder:
`select_questions()`	A new survey containing a subset of the columns
`select_respondents()`	A new survey containing a subset of the rows
`set_pyreadstat_meta_data()`	Use metadata returned from the python package pyreadstat to set properties of the variables (or questions)
`set_valid_and_invalid_variable_values()`	Set the dictionaries of valid and invalid values (and their labels) for selected variables
`set_variable_labels()`	Set the labels (which often is the question text) of selected variables
`set_variable_names()`	Replace the names of selected variables
`set_variable_types()`	Set the type of the variables specified by column_selection
`summarize()`	Create a summary of some interesting aspects of this survey
`variable_info()`	A pandas dataframe containing information about the variables (or questions)