python数据处理之pandas.read_csv（）用法详解_python pandas decimal: optional[str] = ".",

1.读取CSV数据：

def read_csv(
    filepath_or_buffer: FilePathOrBuffer,
    sep=lib.no_default,
    delimiter=None,
    # Column and Index Locations and Names
    header="infer",
    names=None,
    index_col=None,
    usecols=None,
    squeeze=False,
    prefix=None,
    mangle_dupe_cols=True,
    # General Parsing Configuration
    dtype=None,
    engine=None,
    converters=None,
    true_values=None,
    false_values=None,
    skipinitialspace=False,
    skiprows=None,
    skipfooter=0,
    nrows=None,
    # NA and Missing Data Handling
    na_values=None,
    keep_default_na=True,
    na_filter=True,
    verbose=False,
    skip_blank_lines=True,
    # Datetime Handling
    parse_dates=False,
    infer_datetime_format=False,
    keep_date_col=False,
    date_parser=None,
    dayfirst=False,
    cache_dates=True,
    # Iteration
    iterator=False,
    chunksize=None,
    # Quoting, Compression, and File Format
    compression="infer",
    thousands=None,
    decimal: str = ".",
    lineterminator=None,
    quotechar='"',
    quoting=csv.QUOTE_MINIMAL,
    doublequote=True,
    escapechar=None,
    comment=None,
    encoding=None,
    dialect=None,
    # Error Handling
    error_bad_lines=True,
    warn_bad_lines=True,
    # Internal
    delim_whitespace=False,
    low_memory=_c_parser_defaults["low_memory"],
    memory_map=False,
    float_precision=None,
    storage_options: StorageOptions = None,
)

import pandas as pd
# sep表示数据之间的分隔符，如果不指定，则默认为‘，’
data=pd.rean_csv(path,sep=' ')

读取某一CSV文件，但是可以看到其列名称是乱码，这是因为列名称是中文的，为现在的解码方式不能解析中文，所以我们需要修改一下encoding参数设置。

 设置如下：

data=pd.read_csv(path,sep=' ',encoding='gb2312')

 然后可以将读取的CSV数据转换为numpy数据，就可以像数组一样读取了。

data1=np.array（data）

2.将数据存储为CSV文件：

def to_csv(
        self,
        path_or_buf: Optional[FilePathOrBuffer] = None,
        sep: str = ",",
        na_rep: str = "",
        float_format: Optional[str] = None,
        columns: Optional[Sequence[Label]] = None,
        header: Union[bool_t, List[str]] = True,
        index: bool_t = True,
        index_label: Optional[IndexLabel] = None,
        mode: str = "w",
        encoding: Optional[str] = None,
        compression: CompressionOptions = "infer",
        quoting: Optional[int] = None,
        quotechar: str = '"',
        line_terminator: Optional[str] = None,
        chunksize: Optional[int] = None,
        date_format: Optional[str] = None,
        doublequote: bool_t = True,
        escapechar: Optional[str] = None,
        decimal: str = ".",
        errors: str = "strict",
        storage_options: StorageOptions = None,
    )

DataFrame.to_csv(path)

在CSV文件中新增一列并保存：

# 假设data为一个CSV数据，我们需要在这个数据的最后新增一列数据
 
# 新增的数据长度要与data的长度相同
list=[0,1,2,3,4,5,6]
 
# 新增到data上，sorce为新增列的名称
 
data['sorce']=list
 
# 保存,不保存列的编号，编码方式为gbk
 
data.to_csv(path ,encoding='gbk',index=False)