ó áp7]c@sKdZddlZddljjZddljZ ddl Z ddl m Z mZmZmZmZmZmZddlmZmZdd„Zddd„Zdeed „Zed d „Zd „Zd d„Zd„Z d„Z!d„Z"dd„Z#d„Z$d„Z%d„Z&d„Z'de(fd„ƒYZ)ed„Z*dS(s Utility functions models code iÿÿÿÿN(treducetlziptlmaptasstr2trangetlongt string_types(t_is_using_pandast _is_recarrayicCs5i}x(t|ƒD]\}}||||>> import numpy as np >>> import statsmodels.api as sm Univariate examples >>> import string >>> string_var = [string.ascii_lowercase[0:5], string.ascii_lowercase[5:10], string.ascii_lowercase[10:15], string.ascii_lowercase[15:20], string.ascii_lowercase[20:25]] >>> string_var *= 5 >>> string_var = np.asarray(sorted(string_var)) >>> design = sm.tools.categorical(string_var, drop=True) Or for a numerical categorical variable >>> instr = np.floor(np.arange(10,60, step=2)/10) >>> design = sm.tools.categorical(instr, drop=True) With a structured array >>> num = np.random.randn(25,2) >>> struct_ar = np.zeros((25,1), dtype=[('var1', 'f4'),('var2', 'f4'), ('instrument','f4'),('str_instr','a5')]) >>> struct_ar['var1'] = num[:,0][:,None] >>> struct_ar['var2'] = num[:,1][:,None] >>> struct_ar['instrument'] = instr[:,None] >>> struct_ar['str_instr'] = string_var[:,None] >>> design = sm.tools.categorical(struct_ar, col='instrument', drop=True) Or >>> design2 = sm.tools.categorical(struct_ar, col='str_instr', drop=True) iis%Can only convert one column at a timescol must be a str, int or Nones/col must be a str or int when using a DataFramesColumn '{0}' not found in datas"data.name does not match col '{0}'cs+i|]!\}}|ˆkr||“qS(((t.0R tcat(tdummies(s6lib/python2.7/site-packages/statsmodels/tools/tools.pys ¨s s)col is None and the input array is not 1dNtvart_tdtypetusemaskt asrecarraytdatas$Array-like objects are not supportedRR sThe index %s is not understood(5t isinstancetlistttupletlent ValueErrortpdt DataFrametSeriesRtintRt TypeErrortformattnamet Categoricalt get_dummiesR t categoriestcolumnstconcatR"tnamest __class__RtrecarraytsqueezeRt IndexErrorRtuniquetTruetFalsetastypetfloattswapaxesRttolisttshapeRtstrRRtviewttypetnprft drop_fieldst append_fieldstndarraytNotImplementedErrortnewaxistdeletet column_stackR( R%tcolt dictnamestdroptdata_catR R t_swapt tmp_dummytitemtdtR ((Rs6lib/python2.7/site-packages/statsmodels/tools/tools.pyt categorical@sÀN        0  + 1  ! " 8  $  $%      tskipcCsXt|dƒst|ƒrGddlm}||ddd|d|ƒStj|ƒ}|jdkr~|dd…df}n|jd krœtd ƒ‚ntj |d d ƒd k}|tj |d kd d ƒM}|j ƒr|dkrò|S|dkrtdƒ‚qntj |j d ƒ|g}|r8|n|ddd…}tj|ƒS(s‹ Adds a column of ones to an array Parameters ---------- data : array-like ``data`` is the column-ordered design matrix prepend : bool If true, the constant is in the first column. Else the constant is appended (last column). has_constant : str {'raise', 'add', 'skip'} Behavior if ``data`` already has a constant. The default will return data without adding another constant. If 'raise', will raise an error if a constant is present. Using 'add' will duplicate the constant, if one is present. Returns ------- data : array, recarray or DataFrame The original values with a constant (column of ones) as the first or last column. Returned value depends on input type. Notes ----- When the input is recarray or a pandas Series or DataFrame, the added column's name is 'const'. iÿÿÿÿ(t add_trendttrendtctprependt has_constantiNis$Only implementd 2-dimensional arraysRigRXtraises data already contains a constant(RRRtstatsmodels.tsa.tsatoolsRYRt asanyarrayRR*tptptallRtonesRCRN(R%R\R]RYtxtis_nonzero_const((s6lib/python2.7/site-packages/statsmodels/tools/tools.pyt add_constant s$   cCs»tj|ƒ}tj|ƒ}|jdkrF|ddd…f}n|jd|jdkrztd|jdƒ‚ntj||gƒ}tjj|ƒtjj|ƒkr·t St S(s  True if (Q, P) contrast `C` is estimable for (N, P) design `D` From an Q x P contrast matrix `C` and an N x P design matrix `D`, checks if the contrast `C` is estimable by looking at the rank of ``vstack([C,D])`` and verifying it is the same as the rank of `D`. Parameters ---------- C : (Q, P) array-like contrast matrix. If `C` has is 1 dimensional assume shape (1, P) D: (N, P) array-like design matrix Returns ------- tf : bool True if the contrast `C` is estimable on design `D` Examples -------- >>> D = np.array([[1, 1, 1, 0, 0, 0], ... [0, 0, 0, 1, 1, 1], ... [1, 1, 1, 1, 1, 1]]).T >>> isestimable([1, 0, 0], D) False >>> isestimable([1, -1, 0], D) True iNsContrast should have %d columns( RRRRRCR*tvstacktlinalgt matrix_rankR>R=(tCtDtnew((s6lib/python2.7/site-packages/statsmodels/tools/tools.pyt isestimable>s$gV瞯Ò>> from numpy import mean >>> from numpy.random import standard_normal >>> x = standard_normal((3,4,5)) >>> m = mean(x, axis=1) >>> m.shape (3, 5) >>> m = unsqueeze(m, 1, x.shape) >>> m.shape (3, 1, 5) >>> i(R'treshape(R%Rtoldshapetnewshape((s6lib/python2.7/site-packages/statsmodels/tools/tools.pyt unsqueeze¾s  cGstd„|ddd…ƒS(sà Returns the dot product of the given matrices. Parameters ---------- arrs: argument list of ndarray Returns ------- Dot product of all arguments. Examples -------- >>> import numpy as np >>> from statsmodels.tools import chain_dot >>> A = np.arange(1,13).reshape(3,4) >>> B = np.arange(3,15).reshape(4,3) >>> C = np.arange(5,8).reshape(3,1) >>> chain_dot(A,B,C) array([[1820], [4300], [6780]]) cSstj||ƒS(N(RRs(Rdty((s6lib/python2.7/site-packages/statsmodels/tools/tools.pytêtNiÿÿÿÿ(R(tarrs((s6lib/python2.7/site-packages/statsmodels/tools/tools.pyt chain_dotÒscCstjtj|ƒ|dkƒ}tj|dktj|ƒƒ}||}tjtj|ƒtj|ƒƒ}tj||<|S(s¯ Returns np.dot(left_matrix, right_matrix) with the convention that nan * 0 = 0 and nan * x = nan if x != 0. Parameters ---------- A, B : np.ndarrays i(RRsRt nan_to_numR„(tAtBtshould_be_nan_1tshould_be_nan_2t should_be_nanRj((s6lib/python2.7/site-packages/statsmodels/tools/tools.pytnan_dotís !! $ cCst|d|ƒS(sˆ Gets raw results back from wrapped results. Can be used in plotting functions or other post-estimation type routines. t_results(tgetattr(tresults((s6lib/python2.7/site-packages/statsmodels/tools/tools.pytmaybe_unwrap_resultsstBunchcBseZdZd„ZRS(sO Returns a dict-like object with keys accessible via attribute lookup. cOs&tt|ƒj||Ž||_dS(N(tsuperR¯t__init__t__dict__(tselftargstkwargs((s6lib/python2.7/site-packages/statsmodels/tools/tools.pyR±s(t__name__t __module__t__doc__R±(((s6lib/python2.7/site-packages/statsmodels/tools/tools.pyR¯ scCsÁ|dkr|St|dƒ}|jdkrN|rA||jfS|dfSn|jdkrltdƒ‚n|r{|jnd}|rªtj|ƒdd…df|fStj |ƒ|fSdS(sá Parameters ---------- x : array, Series, DataFrame or None Input to verify dimensions, and to transform as necesary ndarray : bool Flag indicating whether to always return a NumPy array. Setting False will return an pandas DataFrame when the input is a Series or a DataFrame. Returns ------- out : array, DataFrame or None array or DataFrame with 2 dimensiona. One dimensional arrays are returned as nobs by 1. None is returned if x is None. names : list of str or None list containing variables names when the input is a pandas datatype. Returns None if the input is an ndarray. Notes ----- Accepts None for simplicity isx mst be 1 or 2-dimensional.N( RRRR5R*R1RRR+R,(RdRJt is_pandasR1((s6lib/python2.7/site-packages/statsmodels/tools/tools.pyt _ensure_2ds   #(+R¸tnumpyRtnumpy.lib.recfunctionstlibt recfunctionsRGt numpy.linalgRhR’tpandasR+tstatsmodels.compat.pythonRRRRRRRtstatsmodels.tools.dataRRRRRR>RWR=RfRmR€RˆRŠRRšRžR£RªR®tdictR¯Rº(((s6lib/python2.7/site-packages/statsmodels/tools/tools.pyts,  4 'Ê4 )