Python DataFrame.from_records方法代码示例

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def test_stata_writer_pandas():
    buf = BytesIO()
    dta = macrodata.load().data
    dtype = dta.dtype
    #as of 0.9.0 pandas only supports i8 and f8
    dta = dta.astype(np.dtype([('year', 'i8'),
                               ('quarter', 'i8')] + dtype.descr[2:]))
    dta4 = dta.astype(np.dtype([('year', 'i4'),
                               ('quarter', 'i4')] + dtype.descr[2:]))
    dta = DataFrame.from_records(dta)
    dta4 = DataFrame.from_records(dta4)
    # dta is int64 'i8'  given to Stata writer
    writer = StataWriter(buf, dta)
    writer.write_file()
    buf.seek(0)
    dta2 = genfromdta(buf)
    dta5 = DataFrame.from_records(dta2)
    # dta2 is int32 'i4'  returned from Stata reader

    if dta5.dtypes[1] is np.dtype('int64'):
        ptesting.assert_frame_equal(dta.reset_index(), dta5)
    else:
        # don't check index because it has different size, int32 versus int64
        ptesting.assert_frame_equal(dta4, dta5[dta5.columns[1:]]) 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def test_datetime_roundtrip():
    dta = np.array([(1, datetime(2010, 1, 1), 2),
                    (2, datetime(2010, 2, 1), 3),
                    (4, datetime(2010, 3, 1), 5)],
                    dtype=[('var1', float), ('var2', object), ('var3', float)])
    buf = BytesIO()
    writer = StataWriter(buf, dta, {"var2" : "tm"})
    writer.write_file()
    buf.seek(0)
    dta2 = genfromdta(buf)
    assert_equal(dta, dta2)

    dta = DataFrame.from_records(dta)
    buf = BytesIO()
    writer = StataWriter(buf, dta, {"var2" : "tm"})
    writer.write_file()
    buf.seek(0)
    dta2 = genfromdta(buf, pandas=True)
    ptesting.assert_frame_equal(dta, dta2.drop('index', axis=1)) 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def fetch_DataFrame(query,
                    dbhandle=None,
                    attach=False):
    '''Fetch query results and returns them as a pandas dataframe'''

    dbhandle = connect(dbhandle, attach=attach)

    cc = dbhandle.cursor()
    sqlresult = cc.execute(query).fetchall()
    cc.close()

    # see http://pandas.pydata.org/pandas-docs/dev/generated/
    # pandas.DataFrame.from_records.html#pandas.DataFrame.from_records
    # this method is design to handle sql_records with proper type
    # conversion

    field_names = [d[0] for d in cc.description]
    pandas_DataFrame = DataFrame.from_records(
        sqlresult,
        columns=field_names)
    return pandas_DataFrame 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def getCryptoHistoricalData(self, symbol, endTime, histPeriod, vwap=False):
		endTimeUNIX = dateToUNIX(endTime)
		startDate = getCurrentDateStr()
		priorDate = datetimeDiff(startDate, histPeriod)
		gdaxTicker = GDAX_TO_POLONIEX[symbol]

		stDateUNIX = dateToUNIX(priorDate)
		eDateUNIX = dateToUNIX(startDate)
		poloniexJsonURL = self.POLO_HIST_DATA.format(gdaxTicker, stDateUNIX, eDateUNIX, self.interval)

		import json
		import requests
		poloniexJson = requests.get(poloniexJsonURL).json()

		from pandas import DataFrame
		histDataframe = DataFrame.from_records(poloniexJson)
		histDataframe.drop('quoteVolume', axis=1, inplace=True)
		histDataframe.drop('weightedAverage', axis=1, inplace=True)
		histDataframe['date'] = histDataframe['date'].astype(float)

		return histDataframe[["date", "open", "high", "low", "close", "volume"]] 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def get_stocks(
        self,
        stockTypeList=['sha', 'shb', 'sza', 'szb'],
        columns=CONST_XUEQIU_QUOTE_ORDER_COLUMN
    ):
        for stockType in stockTypeList:
            print("正在从雪球获取：{}".format(EX_NAME[stockType]))
            page = 1
            while True:
                response = self.session.get(
                    URL_XUEQIU_QUOTE_ORDER(page, columns, stockType),
                    headers=HEADERS_XUEQIU
                ).json()
                df = DataFrame.from_records(
                    response["data"], columns=response["column"])
                if 'stocks' not in locals().keys():
                    stocks = df
                else:
                    stocks = stocks.append(df)
                if df.size == 0:
                    break
                page += 1
        return stocks 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def get_quotation(self, symbol=None, symbolSet=None, dataframe=True, threadNum=3):
        if 'quotation' in self.__dict__.keys():
            del(self.quotation)
            # Cut symbolList
        symbolList = list(symbolSet)
        threads = []
        symbolListSlice = util.slice_list(num=threadNum, data_list=symbolList)
        for symbolList in symbolListSlice:
            loop = asyncio.new_event_loop()
            symbolsList = util.slice_list(step=50, data_list=symbolList)
            tasks = [self.get_quotation_task(
                symbols=symbols) for symbols in symbolsList]
            t = threading.Thread(target=util.thread_loop, args=(loop, tasks))
            threads.append(t)
        for t in threads:
            t.start()
        for t in threads:
            t.join()

        if dataframe:
            self.quotation = DataFrame.from_records(self.quotation).T
        return(self.quotation) 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def test_read_table_buglet_4x_multiindex(self):
        # see gh-6607
        text = """                      A       B       C       D        E
one two three   four
a   b   10.0032 5    -0.5109 -2.3358 -0.4645  0.05076  0.3640
a   q   20      4     0.4473  1.4152  0.2834  1.00661  0.1744
x   q   30      3    -0.6662 -0.5243 -0.3580  0.89145  2.5838"""

        df = self.read_table(StringIO(text), sep=r'\s+')
        assert df.index.names == ('one', 'two', 'three', 'four')

        # see gh-6893
        data = '      A B C\na b c\n1 3 7 0 3 6\n3 1 4 1 5 9'
        expected = DataFrame.from_records(
            [(1, 3, 7, 0, 3, 6), (3, 1, 4, 1, 5, 9)],
            columns=list('abcABC'), index=list('abc'))
        actual = self.read_table(StringIO(data), sep=r'\s+')
        tm.assert_frame_equal(actual, expected) 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def test_frame_from_records_utc(self):
        rec = {'datum': 1.5,
               'begin_time': datetime(2006, 4, 27, tzinfo=pytz.utc)}

        # it works
        DataFrame.from_records([rec], index='begin_time') 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def test_concat_datetime_datetime64_frame(self):
        # #2624
        rows = []
        rows.append([datetime(2010, 1, 1), 1])
        rows.append([datetime(2010, 1, 2), 'hi'])

        df2_obj = DataFrame.from_records(rows, columns=['date', 'test'])

        ind = date_range(start="2000/1/1", freq="D", periods=10)
        df1 = DataFrame({'date': ind, 'test': lrange(10)})

        # it works!
        pd.concat([df1, df2_obj]) 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def test_to_records_with_Mapping_type(self):
        import email
        from email.parser import Parser

        compat.Mapping.register(email.message.Message)

        headers = Parser().parsestr('From: <user@example.com>\n'
                                    'To: <someone_else@example.com>\n'
                                    'Subject: Test message\n'
                                    '\n'
                                    'Body would go here\n')

        frame = DataFrame.from_records([headers])
        all(x in frame for x in ['Type', 'Subject', 'From']) 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def test_resample_segfault():
    # GH 8573
    # segfaulting in older versions
    all_wins_and_wagers = [
        (1, datetime(2013, 10, 1, 16, 20), 1, 0),
        (2, datetime(2013, 10, 1, 16, 10), 1, 0),
        (2, datetime(2013, 10, 1, 18, 15), 1, 0),
        (2, datetime(2013, 10, 1, 16, 10, 31), 1, 0)]

    df = DataFrame.from_records(all_wins_and_wagers,
                                columns=("ID", "timestamp", "A", "B")
                                ).set_index("timestamp")
    result = df.groupby("ID").resample("5min").sum()
    expected = df.groupby("ID").apply(lambda x: x.resample("5min").sum())
    assert_frame_equal(result, expected) 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def test_read_csv_buglet_4x_multi_index2(python_parser_only):
    # see gh-6893
    data = "      A B C\na b c\n1 3 7 0 3 6\n3 1 4 1 5 9"
    parser = python_parser_only

    expected = DataFrame.from_records(
        [(1, 3, 7, 0, 3, 6), (3, 1, 4, 1, 5, 9)],
        columns=list("abcABC"), index=list("abc"))
    result = parser.read_csv(StringIO(data), sep=r"\s+")
    tm.assert_frame_equal(result, expected) 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def recarray_select(recarray, fields):
    """"
    Work-around for changes in NumPy 1.13 that return views for recarray
    multiple column selection
    """
    from pandas import DataFrame
    fields = [fields] if not isinstance(fields, (tuple, list)) else fields
    if len(fields) == len(recarray.dtype):
        selection = recarray
    else:
        recarray = DataFrame.from_records(recarray)
        selection = recarray[fields].to_records(index=False)

    _bytelike_dtype_names(selection)
    return selection 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def webuse(data, baseurl='http://www.stata-press.com/data/r11/', as_df=True):
    """
    Download and return an example dataset from Stata.

    Parameters
    ----------
    data : str
        Name of dataset to fetch.
    baseurl : str
        The base URL to the stata datasets.
    as_df : bool
        If True, returns a `pandas.DataFrame`

    Returns
    -------
    dta : Record Array
        A record array containing the Stata dataset.

    Examples
    --------
    >>> dta = webuse('auto')

    Notes
    -----
    Make sure baseurl has trailing forward slash. Doesn't do any
    error checking in response URLs.
    """
    # lazy imports
    from statsmodels.iolib import genfromdta

    url = urljoin(baseurl, data+'.dta')
    dta = urlopen(url)
    dta = BytesIO(dta.read())  # make it truly file-like
    if as_df:  # could make this faster if we don't process dta twice?
        return DataFrame.from_records(genfromdta(dta))
    else:
        return genfromdta(dta) 

# 需要导入模块: from pandas import DataFrame [as 别名]
# 或者: from pandas.DataFrame import from_records [as 别名]
def test_stata_writer_array():
    buf = BytesIO()
    dta = macrodata.load().data
    dta = DataFrame.from_records(dta)
    dta.columns = ["v%d" % i for i in range(1,15)]
    writer = StataWriter(buf, dta.values)
    writer.write_file()
    buf.seek(0)
    dta2 = genfromdta(buf)
    dta = dta.to_records(index=False)
    assert_array_equal(dta, dta2)