Dj_>dZddlZddlZddlZddlmZddl m Z dZ ddZ ddZ ddZdd Zd Zdd Zd Zd ZdZddZdZdZdZGddeZddZddZy)z Utility functions models code N)_is_using_pandas) array_likec~t|tr|St|tr|jdSt|S)Nlatin1) isinstancestrbytesdecode)ss [C:\Crop_Prediction\Backend\crop-ai-system\venv\Lib\site-packages\statsmodels\tools\tools.pyasstr2r s3!S Au xx!!1v c@i}t|D] \}}||||z<|S)zd Helper function to create a dictionary mapping a column number to the name in tmp_arr. ) enumerate)tmp_arroffsetcol_mapicol_names r _make_dictnamesrs4 G )' 8&F ' Nrctj|}|jdk(r |dddf}|tj|}|jdk(r |dddf}tjtj |j |tj |j |}||||fStj |j |}||S)a Returns views on the arrays Y and X where missing observations are dropped. Y : array_like X : array_like, optional axis : int Axis along which to look for missing observations. Default is 1, ie., observations in rows. Returns ------- Y : ndarray All Y where the X : ndarray Notes ----- If either Y or X is 1d, it is reshaped to be 2d. N)npasarrayndimarray logical_andisnanany)YXaxiskeepidxs r drop_missingr$ s( 1 Avv{ agJ} HHQK 66Q;!T' A.."((1+//$"7!7"$((1+//$"7!79z1W:%%88A;??4((zrctd)ax Construct a dummy matrix from categorical variables .. deprecated:: 0.12 Use pandas.get_dummies instead. Parameters ---------- data : array_like An array, Series or DataFrame. This can be either a 1d vector of the categorical variable or a 2d array with the column specifying the categorical variable specified by the col argument. col : {str, int, None} If data is a DataFrame col must in a column of data. If data is a Series, col must be either the name of the Series or None. For arrays, `col` can be an int that is the (zero-based) column index number. `col` can only be None for a 1d array. The default is None. dictnames : bool, optional If True, a dictionary mapping the column number to the categorical name is returned. Used to have information about plain arrays. drop : bool Whether or not keep the categorical variable in the returned matrix. Returns ------- dummy_matrix : array_like A matrix of dummy (indicator/binary) float variables for the categorical data. dictnames : dict[int, str], optional Mapping between column numbers and categorical names. Notes ----- This returns a dummy variable for *each* distinct variable. If a a DaataFrame is provided, the names for the new variable is the old variable name - underscore - category name. So if the a variable 'vote' had answers as 'yes' or 'no' then the returned array would have to new variables-- 'vote_yes' and 'vote_no'. There is currently no name checking. Examples -------- >>> 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) zcategorical has been removed)NotImplementedError)datacol dictnamesdrops r categoricalr+Gs` < ==rct|drddlm}||d||Stj|}|j }|dk(r |dddf}n|j dkDr t dtj|d dk(}|tj|d k7d z}|jrx|d k(r|S|d k(rl|dk(r t d tj|jd}dj||Dcgc] }t|c}} t d| dtj|jd|g}|r|n|ddd}tj|Scc}w)aq Add a column of ones to an array. Parameters ---------- data : array_like A 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 any column has a constant value. Using 'add' will add a column of 1s if a constant column is present. Returns ------- array_like The original values with a constant (column of ones) as the first or last column. Returned value type depends on input type. Notes ----- When the input is a pandas Series or DataFrame, the added column's name is 'const'. Nr) add_trendc)trendprepend has_constantrz)Only implemented for 2-dimensional arraysr"skipraisezdata is constant.,z Column(s) z are constant.)rstatsmodels.tsa.tsatoolsr-rrr ValueErrorptpallrarangeshapejoinrones column_stack) r'r0r1r-xris_nonzero_constcolumnsr.colss r add_constantrFsX8d#6S' UU 4A 66D qy agJ !DEEvvaa(A-qCxa00 6 !H W $qy !455))AGGAJ/xx9I1J KAQ KL :dV>!BCC  a A !DbD'A ??1  !LsE-ct|dd}t|dd}|jdk(r |dddfn|}|jd|jdk7rtd|jdzt j ||g}tj j|tj j|k7ry y ) a6 True if (Q, P) contrast `c` is estimable for (N, P) design `d`. From an Q x P contrast matrix `C` and an N x P design matrix `D`, checks if the contrast `C` is estimable by looking at the rank of ``vstack([C,D])`` and verifying it is the same as the rank of `D`. Parameters ---------- c : array_like A contrast matrix with shape (Q, P). If 1 dimensional assume shape is (1, P). d : array_like The design matrix, (N, P). Returns ------- bool True if the contrast `c` is estimable on design `d`. Examples -------- >>> d = np.array([[1, 1, 1, 0, 0, 0], ... [0, 0, 0, 1, 1, 1], ... [1, 1, 1, 1, 1, 1]]).T >>> isestimable([1, 0, 0], d) False >>> isestimable([1, -1, 0], d) True r.r2)maxdimdrrNzContrast should have %d columnsFT)rrr>r:rvstacklinalg matrix_rank)r.rInews r isestimablerOs> 1c!$A1c"Affk$' qAwwqzQWWQZ:QWWQZGHH ))QF C yyS!RYY%:%:1%== rc vtj|}|j}tjj |d\}}}tj |}|j d}|j d}|tjj|z}tt||D]} || |kDr d|| z || <d|| <tjtj|tj|ddtjftj|} | |fS)z} Return the pinv of an array X as well as the singular values used in computation. Code adapted from numpy. Frr?r4N)rr conjugaterLsvdcopyr>maximumreducerangemindot transposemultiplynewaxis) rBrcondur vts_origmncutoffrress r pinv_extendedres 1 A Ayy}}Q&HAq" WWQZF  A  A RZZ&&q) )F 3q!9  Q4&=ad7AaDAaD  &&b!2;;qBJJ/?/1||A$@ AC ;rcltj|}tj|tj}tj|j }|}|||j |dkDz||<d|j |z |j |<tj |j |<|S)z Reciprocal of an array with entries less than or equal to 0 set to 0. Parameters ---------- x : array_like The input array. Returns ------- ndarray The array with 0-filled reciprocals. dtyperrQrr zeros_likefloat64rflatnan)rBoutnansposs r reciprrqs 1 A -- ,C 88AFF D %C3x166#;?+CH!&&+%CHHSMVVCHHTN Jrcltj|}tj|tj}tj|j }|}|||j |dk7z||<d|j |z |j |<tj |j |<|S)z Reciprocal of an array with entries less than 0 set to 0. Parameters ---------- x : array_like The input array. Returns ------- ndarray The array with 0-filled reciprocals. rgrrQri)rBrnronon_zeros r recipr0rt/s 1 A -- ,C 88AFF DuH!(+qvvh/?1/DEHXqvvh//CHHXVVCHHTN Jrctjj|dzd}tj|Dcgc] }|dd|f }}tjtj |Scc}w)z Erase columns of zeros: can save some time in pseudoinverse. Parameters ---------- matrix : ndarray The array to clean. Returns ------- ndarray The cleaned array. r2rN)raddrV flatnonzerorrZ)matrixcolsumrvals r clean0r{Gs]VV]]619a (F!#!7 8A6!Q$< 8C 8 88BLL% && 9sA5c|tjj|}tjj|d\}}}tj|}|ddd}g}t |D]}|j |dd||ftjtj|jtjS)a Return an array whose column span is the same as x. Parameters ---------- x : ndarray The array to adjust, 2d. r : int, optional The rank of x. If not provided, determined by `np.linalg.matrix_rank`. Returns ------- ndarray The array adjusted to have full rank. Notes ----- If the rank of x is known it can be specified as r -- no check is made to ensure that this really is the rank of x. NF) full_matricesr8) rrLrMrSargsortrWappendrrZastyperk)rBrvrIr^ordervaluers r fullrankrZs* y II ! !! $iimmAUm3GAq! JJqME $B$KE E 1X% Qq%({^$% ::bll5) * 1 1"** ==rcDt|}d||<|j|S)aW Unsqueeze a collapsed array. Parameters ---------- data : ndarray The data to unsqueeze. axis : int The axis to unsqueeze. oldshape : tuple[int] The original shape before the squeeze or reduce operation. Returns ------- ndarray The unsqueezed array. Examples -------- >>> 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) >>> r)listreshape)r'r"oldshapenewshapes r unsqueezer{s%>H~HHTN << !!rc^tjtj||dk7}tj|dk7tj|}||z}tjtj|tj|}tj||<|S)z Returns np.dot(left_matrix, right_matrix) with the convention that nan * 0 = 0 and nan * x = nan if x != 0. Parameters ---------- A, B : ndarray r)rrYr nan_to_numrm)ABshould_be_nan_1should_be_nan_2 should_be_nanCs r nan_dotrs}ffRXXa[163Offa1frxx{3O#o5M r}}Qq!12AvvAm Hrct|d|S)z Gets raw results back from wrapped results. Can be used in plotting functions or other post-estimation type routines. _results)getattr)resultss r maybe_unwrap_resultsrs 7J 00rc"eZdZdZfdZxZS)Buncha Returns a dict-like object with keys accessible via attribute lookup. Parameters ---------- *args Arguments passed to dict constructor, tuples (key, value). **kwargs Keyword agument passed to dict constructor, key=value. c2t||i|||_yN)super__init____dict__)selfargskwargs __class__s r rzBunch.__init__s $)&) r)__name__ __module__ __qualname____doc__r __classcell__)rs@r rrs rrc*||St|d}|jdk(r|r||jfS|dfS|jdkDr td|r |jnd}|rt j |dddf|fStj||fS)a Parameters ---------- x : ndarray, 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 : ndarray, 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 Nr2zx mst be 1 or 2-dimensional.) rrrDr:namerrpd DataFrame)rBndarray is_pandasrs r _ensure_2drs2 y D)Ivv{ aii< d7N !788166DDzz!}QW%t++||A$$rct|dd}|dk(r||ddtj|dk7df}|tj|dzj dz }|j |z}tj j||d S|d k(rtj j|d \}tjtj|}|9|d|jd ztjtjz}t!||kDj Stj j||S)a( Matrix rank calculation using QR or SVD Parameters ---------- m : array_like A 2-d array-like object to test tol : float, optional The tolerance to use when testing the matrix rank. If not provided an appropriate value is selected. method : {"ip", "qr", "svd"} The method used. "ip" uses the inner-product of a normalized version of m and then computes the rank using NumPy's matrix_rank. "qr" uses a QR decomposition and is the default. "svd" defers to NumPy's matrix_rank. Returns ------- int The rank of m. Notes ----- When using a QR factorization, the rank is determined by the number of elements on the leading diagonal of the R matrix that are above tol in absolute value. rar2rJipNrr3T)tol hermitianqrr)moder)r)rrrsqrtsumTrLrMscipyrabsdiagr>finfofloatepsint)rarmethodrabs_diags r rMrMs8 1c"A ~ aQQ'' ( a Q( ( CC!Gyy$$QC4$@@ 4 \\__QS_ )66"''!*% ;1+ *RXXe_-@-@@CHsN'')**yy$$QC$00r)r)Nr)NFF)Tr5)gV瞯rs33 NP>h7t'T000'&>B!"H .1 D  (%V)1r