Question

我对数据挖掘很感兴趣，我想打开并使用yelp的数据。 Yelp的数据是json格式，在它的网站上，它有以下代码将json转换为csv。但是，当我打开命令行并写下以下内容时：

$ python json_to_csv_converter.py yelp_academic_dataset.json

我收到错误。你能帮帮我吗？

代码是：

# -*- coding: utf-8 -*-
"""Convert the Yelp Dataset Challenge dataset from json format to csv.
For more information on the Yelp Dataset Challenge please visit http://yelp.com/dataset_challenge
"""
import argparse
import collections
import csv
import simplejson as json


def read_and_write_file(json_file_path, csv_file_path, column_names):
    """Read in the json dataset file and write it out to a csv file, given the column names."""
    with open(csv_file_path, 'wb+') as fout:
        csv_file = csv.writer(fout)
        csv_file.writerow(list(column_names))
        with open(json_file_path) as fin:
            for line in fin:
                line_contents = json.loads(line)
                csv_file.writerow(get_row(line_contents, column_names))

def get_superset_of_column_names_from_file(json_file_path):
    """Read in the json dataset file and return the superset of column names."""
    column_names = set()
    with open(json_file_path) as fin:
        for line in fin:
            line_contents = json.loads(line)
            column_names.update(
                    set(get_column_names(line_contents).keys())
                    )
    return column_names

def get_column_names(line_contents, parent_key=''):
    """Return a list of flattened key names given a dict.
    Example:
        line_contents = {
            'a': {
                'b': 2,
                'c': 3,
                },
        }
        will return: ['a.b', 'a.c']
    These will be the column names for the eventual csv file.
    """
    column_names = []
    for k, v in line_contents.iteritems():
        column_name = "{0}.{1}".format(parent_key, k) if parent_key else k
        if isinstance(v, collections.MutableMapping):
            column_names.extend(
                    get_column_names(v, column_name).items()
                    )
        else:
            column_names.append((column_name, v))
    return dict(column_names)

def get_nested_value(d, key):
    """Return a dictionary item given a dictionary `d` and a flattened key from `get_column_names`.

    Example:
        d = {
            'a': {
                'b': 2,
                'c': 3,
                },
        }
        key = 'a.b'
        will return: 2

    """
    if '.' not in key:
        if key not in d:
            return None
        return d[key]
    base_key, sub_key = key.split('.', 1)
    if base_key not in d:
        return None
    sub_dict = d[base_key]
    return get_nested_value(sub_dict, sub_key)

def get_row(line_contents, column_names):
    """Return a csv compatible row given column names and a dict."""
    row = []
    for column_name in column_names:
        line_value = get_nested_value(
                        line_contents,
                        column_name,
                        )
        if isinstance(line_value, unicode):
            row.append('{0}'.format(line_value.encode('utf-8')))
        elif line_value is not None:
            row.append('{0}'.format(line_value))
        else:
            row.append('')
    return row

if __name__ == '__main__':
    """Convert a yelp dataset file from json to csv."""

    parser = argparse.ArgumentParser(
            description='Convert Yelp Dataset Challenge data from JSON format to CSV.',
            )

    parser.add_argument(
            'json_file',
            type=str,
            help='The json file to convert.',
            )

    args = parser.parse_args()

    json_file = args.json_file
    csv_file = '{0}.csv'.format(json_file.split('.json')[0])

    column_names = get_superset_of_column_names_from_file(json_file)
    read_and_write_file(json_file, csv_file, column_names)

我在命令行中出错：

Traceback (most recent call last):
File "json_to_csv_converter.py", line 122, in column_names=get_superset_of_column_names_from_file
File "json_to_csv_converter.py", line 25, in get_superset_of_column_names_from_file
for line in fin:
File "C:\Users\Bengi\Appdata\Local\Programs\Python\Python35-32\lib\encodings\cp1252.py" line 23, in decode
return codecs.charmap_decode(input, self_errors,decoding_table)[0]
Unicode Decode Error: 'charmap' codec cant decode byte 0X9d in position 1102: character maps to

Answer 1

你有文件编码问题吗？你应该把encoding =＆＃39; utf8＆＃39;在json文件打开函数之后：with open(json_file_path, encoding='utf8') as fin:

Answer 2

根据错误消息判断输入文件似乎有问题。看起来json_to_csv_converter.py确定文件编码是Windows 1252，但文件中有一个或多个无效字符，即'\x9d'，这不是有效的1252代码点。

检查您的文件是否已正确编码。我猜这个文件是UTF8编码的，但由于某种原因它正在被处理，好像它是Windows 1252.你编辑了文件吗？

JSON到CSV转换器-YELP Data Set-python

2 个答案: