python 程序员的数学2之survey.py

这篇是在看程序员的数学2的学习笔记，下面是survey.py的代码注解

"""This file contains code for use with "Think Stats",
by Allen B. Downey, available from greenteapress.com

Copyright 2010 Allen B. Downey
License: GNU GPLv3 http://www.gnu.org/licenses/gpl.html
"""

import sys
import gzip
import os

class Record(object):
    """Represents a record."""

class Respondent(Record): #先创建两个空的类，被调查的和怀孕的，然后再后面填补
    """Represents a respondent."""

class Pregnancy(Record):
    """Represents a pregnancy."""

class Table(object):
    """Represents a table as a list of objects"""

    def __init__(self):
        self.records = []  #此处初始化了records，records表示Record对象的列表

    def __len__(self):
        return len(self.records)

    def ReadFile(self, data_dir, filename, fields, constructor, n=None):
        """Reads a compressed data file builds one object per record.

        Args:
            data_dir: string directory name 数据集目录
            filename: string name of the file to read 文件的名称

            fields: sequence of (name, start, end, case) tuples specifying 
            the fields to extract  记录的集合表示字段，case表示类型转换

            constructor: what kind of object to create  新建一个对象，也就是在后面创建Respondent和Pregnancy,这样就填充了前面定义的空类        """
        filename = os.path.join(data_dir, filename) 

        if filename.endswith('gz'):
            fp = gzip.open(filename)
        else:
            fp = open(filename)

        for i, line in enumerate(fp):#i相当于是索引,line 就是读取每一行
            if i == n:
                break  #如果i到了最后一行，就停止然后跳出循环
            record = self.MakeRecord(line, fields, constructor)#相当于文件打开之后，就不再是filename，而是line，这里line表示所有行的文件内容
            self.AddRecord(record)
        fp.close()

    def MakeRecord(self, line, fields, constructor):
        """Scans a line and returns an object with the appropriate fields.

        Args:
            line: string line from a data file

            fields: sequence of (name, start, end, cast) tuples specifying 
            the fields to extract

            constructor: callable that makes an object for the record.

        Returns:
            Record with appropriate fields.
        """
        obj = constructor()#创建一个新的对象
        for (field, start, end, cast) in fields:
            try:
                s = line[start-1:end]
                val = cast(s)
            except ValueError:
                # If you are using Visual Studio, you might see an
                # "error" at this point, but it is not really an error;
                # I am just using try...except to handle not-available (NA)
                # data.  You should be able to tell Visual Studio to
                # ignore this non-error.
                val = 'NA'
            setattr(obj, field, val)#obj.field = val
        return obj

    def AddRecord(self, record):
        """Adds a record to this table.

        Args:
            record: an object of one of the record types.
        """
        self.records.append(record)#增加记录

    def ExtendRecords(self, records):
        """Adds records to this table.

        Args:
            records: a sequence of record object
        """
        self.records.extend(records)#增加一段记录

    def Recode(self):
        """Child classes can override this to recode values."""
        pass


class Respondents(Table):
    """Represents the respondent table."""

    def ReadRecords(self, data_dir='.', n=None):
        filename = self.GetFilename()
        self.ReadFile(data_dir, filename, self.GetFields(), Respondent, n)#这里Respondent=constructor
        self.Recode()

    def GetFilename(self):
        return '2002FemResp.dat.gz'

    def GetFields(self):
        """Returns a tuple specifying the fields to extract.

        The elements of the tuple are field, start, end, case.

                field is the name of the variable
                start and end are the indices as specified in the NSFG docs
                cast is a callable that converts the result to int, float, etc.
        """
        return [
            ('caseid', 1, 12, int),
            ]

class Pregnancies(Table):
    """Contains survey data about a Pregnancy."""

    def ReadRecords(self, data_dir='.', n=None):
        filename = self.GetFilename()
        self.ReadFile(data_dir, filename, self.GetFields(), Pregnancy, n)
        self.Recode()

    def GetFilename(self):
        return '2002FemPreg.dat.gz'

    def GetFields(self):
        """Gets information about the fields to extract from the survey data.

        Documentation of the fields for Cycle 6 is at
        http://nsfg.icpsr.umich.edu/cocoon/WebDocs/NSFG/public/index.htm

        Returns:
            sequence of (name, start, end, type) tuples
        """
        return [
            ('caseid', 1, 12, int),
            ('nbrnaliv', 22, 22, int),
            ('babysex', 56, 56, int),
            ('birthwgt_lb', 57, 58, int),
            ('birthwgt_oz', 59, 60, int),
            ('prglength', 275, 276, int),
            ('outcome', 277, 277, int),
            ('birthord', 278, 279, int),
            ('agepreg', 284, 287, int),
            ('finalwgt', 423, 440, float),
            ]

    def Recode(self):
        for rec in self.records:

            # divide mother's age by 100
            try:
                if rec.agepreg != 'NA':
                    rec.agepreg /= 100.0
            except AttributeError:
                pass

            # convert weight at birth from lbs/oz to total ounces
            # note: there are some very low birthweights
            # that are almost certainly errors, but for now I am not
            # filtering
            try:
                if (rec.birthwgt_lb != 'NA' and rec.birthwgt_lb < 20 and
                    rec.birthwgt_oz != 'NA' and rec.birthwgt_oz <= 16):
                    rec.totalwgt_oz = rec.birthwgt_lb * 16 + rec.birthwgt_oz
                else:
                    rec.totalwgt_oz = 'NA'
            except AttributeError:
                pass


def main(name, data_dir='.'):
    resp = Respondents()
    resp.ReadRecords(data_dir)
    print 'Number of respondents', len(resp.records)

    preg = Pregnancies()
    preg.ReadRecords(data_dir)
    print 'Number of pregnancies', len(preg.records)


if __name__ == '__main__':
    main(*sys.argv)

基类：Record、Table
子类：
Respondent、Pregnancy->Record 一开始并没有直接给这两个子类初始化，而是通过在Table里面创建这两个子类为对象，然后添加内容
Respondents、Pregnancies->Table 就是在这两个类里面读取文件，给对象添加字段

Table的函数：

__init__()
__len__()
ReadFile()#打开文件
MakeRecord()
AddRecord()
ExtendRecords()
Record()

Respondent的函数：

ReadRecords()
       GetFilename()
       ReadFile()
       Record()
GetFilename()
Getfields()

Pregnancies的函数：

ReadRecords()
GetFilename()
GetFields()
Record()