愉快的学习就从翻译开始吧_2-Time Series Forecasting with the Long Short-Term Memory Network in Python

Persistence Model Forecast/持续性模型预测（因为是一个一个的预测，所以我认为就是持续不断的预测，也就是持续预测，持久性预测？见鬼去吧）

A good baseline forecast for a time series with a linear increasing trend is a persistence forecast.

对一个具有线性增长的时间序列比较好的基准预测是持续性预测

The persistence forecast is where the observation from the prior time step (t-1) is used to predict the observation at the current time step (t).

持续性预测是用前一个时间步的观测值来预测当前时间步的观测值（看到了吧，这玩意就像迭代一样，就是持续性的）

We can implement this by taking the last observation from the training data and history accumulated by walk-forward validation and using that to predict the current time step.

我们可以通过从训练数据和前向验证积累的历史记录中获取最后一个观测值并使用它来预测当前时间步来实现此目的。

For example:

1 2	# make prediction yhat = history [ - 1 ]

We will accumulate all predictions in an array so that they can be directly compared to the test dataset.

我们将所有的预测结果累加到一个阵列中，以便它们可以直接与测试数据集进行对比

The complete example of the persistence forecast model on the Shampoo Sales dataset is listed below.

洗发水数据集持续性预测模型的完整示例如下：

from pandas import read_csv
from pandas import datetime
from sklearn.metrics import mean_squared_error
from math import sqrt
from matplotlib import pyplot
# load dataset
def parser(x):
	return datetime.strptime('190'+x, '%Y-%m')
series = read_csv('shampoo-sales.csv', header=0, parse_dates=[0], index_col=0, squeeze=True, date_parser=parser)
# split data into train and test
X = series.values
train, test = X[0:-12], X[-12:]
# walk-forward validation
history = [x for x in train]
predictions = list()
for i in range(len(test)):
	# make prediction
	predictions.append(history[-1])
	# observation
	history.append(test[i])
# report performance
rmse = sqrt(mean_squared_error(test, predictions))
print('RMSE: %.3f' % rmse)
# line plot of observed vs predicted
pyplot.plot(test)
pyplot.plot(predictions)
pyplot.show()

Running the example prints the RMSE of about 136 monthly shampoo sales for the forecasts on the test dataset.

运行该示例打印测试数据集上的每月洗发水销售量的均方根误差约为136。

RMSE: 136.761

A line plot of the test dataset (blue) compared to the predicted values (orange) is also created showing the persistence model forecast in context.

测试数据集（蓝色）对比预测数据（黄色）的线图被创建，持续性模型预测显示在图表下方

For more on the persistence model for time series forecasting, see this post:

想了解更多时间序列预测的持续性模型，看下面这篇文章（鬼才想去了解，这种几乎毫无价值的预测模型）

• How to Make Baseline Predictions for Time Series Forecasting with Python

Now that we have a baseline of performance on the dataset, we can get started developing an LSTM model for the data

现在我们有了一个数据集的性能基准，我们可以为这些数据开发LSTM模型了

（折腾了这么久，也就用训练集中的最后一个值和测试集中的前11个值是构造了一个predictions序列，然后计算其和test序列的均方根差，预测原理就是认为上个月的销量，就是本月的销量，算是最最基础的预测吧，可以看出这老外的文章叙述还是有点瑕疵的，很多地方只能靠意会，无奈，既然开了头就坚持弄下去吧，下一节就正式到LSTM了）

pandas.read_csv

pandas. read_csv ( filepath_or_buffer,  sep=',  ',  delimiter=None,  header='infer',  names=None,  index_col=None,  usecols=None,  squeeze=False,  prefix=None,  mangle_dupe_cols=True,  dtype=None,  engine=None,  converters=None,  true_values=None,  false_values=None,  skipinitialspace=False,  skiprows=None,  nrows=None,  na_values=None,  keep_default_na=True,  na_filter=True,  verbose=False,  skip_blank_lines=True,  parse_dates=False,  infer_datetime_format=False,  keep_date_col=False,  date_parser=None,  dayfirst=False,  iterator=False,  chunksize=None,  compression='infer',  thousands=None,  decimal=b'.',  lineterminator=None,  quotechar='"',  quoting=0,  escapechar=None,  comment=None,  encoding=None,  dialect=None,  tupleize_cols=None,  error_bad_lines=True,  warn_bad_lines=True,  skipfooter=0,  doublequote=True,  delim_whitespace=False,  low_memory=True,  memory_map=False,  float_precision=None ) [source]

Read CSV (comma-separated) file into DataFrame

Also supports optionally iterating or breaking of the file into chunks.

Additional help can be found in the online docs for IO Tools.

Parameters:

filepath_or_buffer  :  str, pathlib.Path, py._path.local.LocalPath or any \ object with a read() method (such as a file handle or StringIO) The string could be a URL. Valid URL schemes include http, ftp, s3, and file. For file URLs, a host is expected. For instance, a local file could be file://localhost/path/to/table.csv sep : str, default ‘,’ Delimiter to use. If sep is None, the C engine cannot automatically detect the separator, but the Python parsing engine can, meaning the latter will be used and automatically detect the separator by Python’s builtin sniffer tool, csv.Sniffer. In addition, separators longer than 1 character and different from '\s+' will be interpreted as regular expressions and will also force the use of the Python parsing engine. Note that regex delimiters are prone to ignoring quoted data. Regex example: '\r\t' delimiter : str, default None Alternative argument name for sep. delim_whitespace : boolean, default False Specifies whether or not whitespace (e.g. ' ' or '\t') will be used as the sep. Equivalent to setting sep='\s+'. If this option is set to True, nothing should be passed in for the delimiter parameter. New in version 0.18.1: support for the Python parser. header : int or list of ints, default ‘infer’ Row number(s) to use as the column names, and the start of the data. Default behavior is to infer the column names: if no names are passed the behavior is identical to header=0 and column names are inferred from the first line of the file, if column names are passed explicitly then the behavior is identical to header=None. Explicitly pass header=0 to be able to replace existing names. The header can be a list of integers that specify row locations for a multi-index on the columns e.g. [0,1,3]. Intervening rows that are not specified will be skipped (e.g. 2 in this example is skipped). Note that this parameter ignores commented lines and empty lines ifskip_blank_lines=True, so header=0 denotes the first line of data rather than the first line of the file. names : array-like, default None List of column names to use. If file contains no header row, then you should explicitly pass header=None. Duplicates in this list will cause a UserWarning to be issued. index_col : int or sequence or False, default None Column to use as the row labels of the DataFrame. If a sequence is given, a MultiIndex is used. If you have a malformed file with delimiters at the end of each line, you might consider index_col=False to force pandas to _not_ use the first column as the index (row names) usecols : list-like or callable, default None Return a subset of the columns. If list-like, all elements must either be positional (i.e. integer indices into the document columns) or strings that correspond to column names provided either by the user in names or inferred from the document header row(s). For example, a valid list-like usecols parameter would be [0, 1, 2] or [‘foo’, ‘bar’, ‘baz’]. Element order is ignored, so usecols=[0, 1] is the same as [1, 0]. To instantiate a DataFrame from data with element order preserved use pd.read_csv(data,usecols=['foo', 'bar'])[['foo', 'bar']] for columns in ['foo', 'bar'] order orpd.read_csv(data, usecols=['foo', 'bar'])[['bar', 'foo']] for ['bar', 'foo'] order. If callable, the callable function will be evaluated against the column names, returning names where the callable function evaluates to True. An example of a valid callable argument would be lambda x: x.upper() in ['AAA', 'BBB', 'DDD']. Using this parameter results in much faster parsing time and lower memory usage. squeeze : boolean, default False If the parsed data only contains one column then return a Series prefix : str, default None Prefix to add to column numbers when no header, e.g. ‘X’ for X0, X1, … mangle_dupe_cols : boolean, default True Duplicate columns will be specified as ‘X’, ‘X.1’, …’X.N’, rather than ‘X’…’X’. Passing in False will cause data to be overwritten if there are duplicate names in the columns. dtype : Type name or dict of column -> type, default None Data type for data or columns. E.g. {‘a’: np.float64, ‘b’: np.int32} Use str or object together with suitable na_values settings to preserve and not interpret dtype. If converters are specified, they will be applied INSTEAD of dtype conversion. engine : {‘c’, ‘python’}, optional Parser engine to use. The C engine is faster while the python engine is currently more feature-complete. converters : dict, default None Dict of functions for converting values in certain columns. Keys can either be integers or column labels true_values : list, default None Values to consider as True false_values : list, default None Values to consider as False skipinitialspace : boolean, default False Skip spaces after delimiter. skiprows : list-like or integer or callable, default None Line numbers to skip (0-indexed) or number of lines to skip (int) at the start of the file. If callable, the callable function will be evaluated against the row indices, returning True if the row should be skipped and False otherwise. An example of a valid callable argument would be lambda x: x in [0, 2]. skipfooter : int, default 0 Number of lines at bottom of file to skip (Unsupported with engine=’c’) nrows : int, default None Number of rows of file to read. Useful for reading pieces of large files na_values : scalar, str, list-like, or dict, default None Additional strings to recognize as NA/NaN. If dict passed, specific per-column NA values. By default the following values are interpreted as NaN: ‘’, ‘#N/A’, ‘#N/A N/A’, ‘#NA’, ‘-1.#IND’, ‘-1.#QNAN’, ‘-NaN’, ‘-nan’, ‘1.#IND’, ‘1.#QNAN’, ‘N/A’, ‘NA’, ‘NULL’, ‘NaN’, ‘n/a’, ‘nan’, ‘null’. keep_default_na : bool, default True Whether or not to include the default NaN values when parsing the data. Depending on whether na_values is passed in, the behavior is as follows: If keep_default_na is True, and na_values are specified, na_values is appended to the default NaN values used for parsing. If keep_default_na is True, and na_values are not specified, only the default NaN values are used for parsing. If keep_default_na is False, and na_values are specified, only the NaN values specified na_values are used for parsing. If keep_default_na is False, and na_values are not specified, no strings will be parsed as NaN. Note that if na_filter is passed in as False, the keep_default_na and na_values parameters will be ignored. na_filter : boolean, default True Detect missing value markers (empty strings and the value of na_values). In data without any NAs, passing na_filter=False can improve the performance of reading a large file verbose : boolean, default False Indicate number of NA values placed in non-numeric columns skip_blank_lines : boolean, default True If True, skip over blank lines rather than interpreting as NaN values parse_dates : boolean or list of ints or names or list of lists or dict, default False boolean. If True -> try parsing the index. list of ints or names. e.g. If [1, 2, 3] -> try parsing columns 1, 2, 3 each as a separate date column. list of lists. e.g. If [[1, 3]] -> combine columns 1 and 3 and parse as a single date column. dict, e.g. {‘foo’ : [1, 3]} -> parse columns 1, 3 as date and call result ‘foo’ If a column or index contains an unparseable date, the entire column or index will be returned unaltered as an object data type. For non-standard datetime parsing, use pd.to_datetime after pd.read_csv Note: A fast-path exists for iso8601-formatted dates. infer_datetime_format : boolean, default False If True and parse_dates is enabled, pandas will attempt to infer the format of the datetime strings in the columns, and if it can be inferred, switch to a faster method of parsing them. In some cases this can increase the parsing speed by 5-10x. keep_date_col : boolean, default False If True and parse_dates specifies combining multiple columns then keep the original columns. date_parser : function, default None Function to use for converting a sequence of string columns to an array of datetime instances. The default uses dateutil.parser.parser to do the conversion. Pandas will try to call date_parser in three different ways, advancing to the next if an exception occurs: 1) Pass one or more arrays (as defined by parse_dates) as arguments; 2) concatenate (row-wise) the string values from the columns defined by parse_datesinto a single array  and pass that; and 3) call date_parser once for each row using one or more strings (corresponding to the columns defined by parse_dates) as arguments. dayfirst : boolean, default False DD/MM format dates, international and European format iterator : boolean, default False Return TextFileReader object for iteration or getting chunks with get_chunk(). chunksize : int, default None Return TextFileReader object for iteration. See the IO Tools docs for more information on iterator and chunksize. compression : {‘infer’, ‘gzip’, ‘bz2’, ‘zip’, ‘xz’, None}, default ‘infer’ For on-the-fly decompression of on-disk data. If ‘infer’ and filepath_or_buffer is path-like, then detect compression from the following extensions: ‘.gz’, ‘.bz2’, ‘.zip’, or ‘.xz’ (otherwise no decompression). If using ‘zip’, the ZIP file must contain only one data file to be read in. Set to None for no decompression. New in version 0.18.1: support for ‘zip’ and ‘xz’ compression. thousands : str, default None Thousands separator decimal : str, default ‘.’ Character to recognize as decimal point (e.g. use ‘,’ for European data). float_precision : string, default None Specifies which converter the C engine should use for floating-point values. The options are None for the ordinary converter, high for the high-precision converter, and round_trip for the round-trip converter. lineterminator : str (length 1), default None Character to break file into lines. Only valid with C parser. quotechar : str (length 1), optional The character used to denote the start and end of a quoted item. Quoted items can include the delimiter and it will be ignored. quoting : int or csv.QUOTE_* instance, default 0 Control field quoting behavior per csv.QUOTE_* constants. Use one of QUOTE_MINIMAL (0), QUOTE_ALL (1), QUOTE_NONNUMERIC (2) or QUOTE_NONE (3). doublequote : boolean, default True When quotechar is specified and quoting is not QUOTE_NONE, indicate whether or not to interpret two consecutive quotechar elements INSIDE a field as a single quotechar element. escapechar : str (length 1), default None One-character string used to escape delimiter when quoting is QUOTE_NONE. comment : str, default None Indicates remainder of line should not be parsed. If found at the beginning of a line, the line will be ignored altogether. This parameter must be a single character. Like empty lines (as long as skip_blank_lines=True), fully commented lines are ignored by the parameter header but not by skiprows. For example, if comment='#', parsing#empty\na,b,c\n1,2,3 with header=0 will result in ‘a,b,c’ being treated as the header. encoding : str, default None Encoding to use for UTF when reading/writing (ex. ‘utf-8’). List of Python standard encodings dialect : str or csv.Dialect instance, default None If provided, this parameter will override values (default or not) for the following parameters: delimiter, doublequote, escapechar, skipinitialspace, quotechar, and quoting. If it is necessary to override values, a ParserWarning will be issued. See csv.Dialect documentation for more details. tupleize_cols : boolean, default False Deprecated since version 0.21.0: This argument will be removed and will always convert to MultiIndex Leave a list of tuples on columns as is (default is to convert to a MultiIndex on the columns) error_bad_lines : boolean, default True Lines with too many fields (e.g. a csv line with too many commas) will by default cause an exception to be raised, and no DataFrame will be returned. If False, then these “bad lines” will dropped from the DataFrame that is returned. warn_bad_lines : boolean, default True If error_bad_lines is False, and warn_bad_lines is True, a warning for each “bad line” will be output. low_memory : boolean, default True Internally process the file in chunks, resulting in lower memory use while parsing, but possibly mixed type inference. To ensure no mixed types either set False, or specify the type with the dtype parameter. Note that the entire file is read into a single DataFrame regardless, use the chunksize or iterator parameter to return the data in chunks. (Only valid with C parser) memory_map : boolean, default False If a filepath is provided for filepath_or_buffer, map the file object directly onto memory and access the data directly from there. Using this option can improve performance because there is no longer any I/O overhead.

Returns:

result  :  DataFrame or TextParser