def read(filename, sep=None, header=True, verbose=True):
"""
Read a CSV file.
Parameters
----------
filename : str
Path to a CSV file.
sep : str
Separator. ``None`` triggers auto-detection. Defaults to ``None``.
header : bool
``True`` for file with a header; ``False`` otherwise. Defaults
to ``True``.
verbose : bool
`True` for progress information; `False` otherwise.
Returns
-------
data : dask dataframes
Examples
--------
.. doctest::
>>> from limix.io.csv import read
>>> from limix import file_example
>>>
>>> with file_example("data.csv") as filepath:
... df = read(filepath, verbose=False)
... print(df) # doctest: +FLOAT_CMP
pheno attr1 attr2 attr3
0 sex string 10 a
1 size float -3 b
2 force int f c
"""
from dask.dataframe import read_csv as dask_read_csv
from pandas import read_csv as pandas_read_csv
from .._display import session_line
if sep is None:
sep = _infer_separator(filename)
header = 0 if header else None
with session_line("Reading {}... ".format(filename), disable=not verbose):
if _is_large_file(filename):
df = dask_read_csv(filename, sep=sep, header=header)
else:
df = pandas_read_csv(filename, sep=sep, header=header)
if len(df.columns) > 0:
if df.columns[0] == "Unnamed: 0":
df = df.set_index("Unnamed: 0")
df.index.name = None
return df
def read_csv(cls, filename, sampling_rate=1.0, *args, **kwargs):
"""Read comma-separated file.
Parameters
----------
filename : str
Filename for the csv file
Returns
-------
eeg_run : EEGRun
EEGRun dataframe with read data.
"""
return cls(pandas_read_csv(filename, *args, **kwargs),
sampling_rate=sampling_rate)
def read_csv(cls, filename, sampling_rate=None, *args, **kwargs):
"""Read comma-separated file.
Parameters
----------
filename : str
Filename for the csv file
Returns
-------
eeg_run : EEGAuxRun
EEGAuxRun dataframe with read data.
"""
return EEGAuxRun(pandas_read_csv(filename, *args, **kwargs),
sampling_rate=sampling_rate)
def read_csv(cls, filename, sampling_rate=None, *args, **kwargs):
"""Read comma-separated file.
Parameters
----------
filename : str
Filename for the csv file
Returns
-------
eeg_run : EEGElectrodeRun
EEGElectrodeRun dataframe with read data.
"""
# TODO: This will not instance in derived class.
return EEGElectrodeRun(pandas_read_csv(filename, *args, **kwargs),
sampling_rate=sampling_rate)
def read_csv(cls, filename, sampling_rate=None, *args, **kwargs):
"""Read comma-separated file.
Parameters
----------
filename : str
Filename for the csv file
Returns
-------
eeg_run : EEGRun
EEGRun dataframe with read data.
"""
# TODO: This will not instance in derived class.
return EEGRun(pandas_read_csv(filename, *args, **kwargs),
sampling_rate=sampling_rate)
def gameInfoDownloadForAllPlayers(restoreMainPath):
"""
// 文件保存主目录 restoreMainPath
// 一旦发生异常，则捕获并更新infoOfAllPlayers到本地
"""
"""
// 读取infoOfAllPlayers，若本地不存在，则新建并初始化
"""
try:
if (os_path_exists(restoreMainPath + "\infoOfAllPlayers.csv")):
infoOfAllPlayers = pandas_read_csv(restoreMainPath +
"\infoOfAllPlayers.csv")
print("已读取本地球员基本信息")
else:
infoOfAllPlayers = filterDataForAllPlayers()
infoOfAllPlayers["downloaded"] = "No"
print("创建本地球员基本信息")
for ii in range(0, len(infoOfAllPlayers)):
restoreFilePathOfPlayer = restoreMainPath + "\\" + infoOfAllPlayers[
"playerName"][ii]
if (infoOfAllPlayers["downloaded"][ii] == "No"):
if (os_path_exists(restoreFilePathOfPlayer)):
shutil_rmtree(restoreFilePathOfPlayer)
print("{0}信息不完整，删除重建".format(
infoOfAllPlayers["playerName"][ii]))
if (os_mkdir(restoreFilePathOfPlayer) == False):
print("文件夹{0}创建不成功".format(restoreFilePathOfPlayer))
raise Exception()
"""
// 获取球员所有赛季的统计信息链接页面
"""
print("开始获取{0}信息".format(infoOfAllPlayers["playerName"][ii]))
allSeasonWebLog = filterDataForallSeasonWebLog(
infoOfAllPlayers["mainPageUrl"][ii])
for singleSeasonWebLog in allSeasonWebLog:
res = requests_get(singleSeasonWebLog)
strOfSeasonPage = res.text
"""
// 保存常规赛和季后赛每场比赛数据到本地
"""
yearStr = singleSeasonWebLog[-5:-1] #有可能为无效链接，最后四位非数字
if (yearStr.isdigit()):
filterDataForRegularSeason(strOfSeasonPage).to_csv(restoreFilePathOfPlayer + "\\" \
+ "regularSeason" + singleSeasonWebLog[-5:-1] + ".csv")
filterDataForPlayOffs(strOfSeasonPage).to_csv(restoreFilePathOfPlayer + "\\" \
+ "playOffs" + singleSeasonWebLog[-5:-1] + ".csv")
else:
continue
"""
// 该球员信息保存成功
"""
infoOfAllPlayers["downloaded"][ii] = "Yes"
else:
print("{0}信息已下载".format(infoOfAllPlayers["playerName"][ii]))
continue
except Exception as e:
infoOfAllPlayers.to_csv(restoreMainPath + "\infoOfAllPlayers.csv")
print(e)
print("本地球员基本信息已更新")
else:
infoOfAllPlayers.to_csv(restoreMainPath + "\infoOfAllPlayers.csv")
print("下载完成")