MCPcopy Create free account
hub / github.com/numpy/numpy / fit

Method fit

numpy/polynomial/_polybase.py:956–1045  ·  view source on GitHub ↗

Least squares fit to data. Return a series instance that is the least squares fit to the data `y` sampled at `x`. The domain of the returned instance can be specified and this will often result in a superior fit with less chance of ill conditioning. Paramete

(cls, x, y, deg, domain=None, rcond=None, full=False, w=None,
        window=None, symbol='x')

Source from the content-addressed store, hash-verified

954
955 @classmethod
956 def fit(cls, x, y, deg, domain=None, rcond=None, full=False, w=None,
957 window=None, symbol='x'):
958 """Least squares fit to data.
959
960 Return a series instance that is the least squares fit to the data
961 `y` sampled at `x`. The domain of the returned instance can be
962 specified and this will often result in a superior fit with less
963 chance of ill conditioning.
964
965 Parameters
966 ----------
967 x : array_like, shape (M,)
968 x-coordinates of the M sample points ``(x[i], y[i])``.
969 y : array_like, shape (M,)
970 y-coordinates of the M sample points ``(x[i], y[i])``.
971 deg : int or 1-D array_like
972 Degree(s) of the fitting polynomials. If `deg` is a single integer
973 all terms up to and including the `deg`'th term are included in the
974 fit. For NumPy versions >= 1.11.0 a list of integers specifying the
975 degrees of the terms to include may be used instead.
976 domain : {None, [beg, end], []}, optional
977 Domain to use for the returned series. If ``None``,
978 then a minimal domain that covers the points `x` is chosen. If
979 ``[]`` the class domain is used. The default value was the
980 class domain in NumPy 1.4 and ``None`` in later versions.
981 The ``[]`` option was added in numpy 1.5.0.
982 rcond : float, optional
983 Relative condition number of the fit. Singular values smaller
984 than this relative to the largest singular value will be
985 ignored. The default value is len(x)*eps, where eps is the
986 relative precision of the float type, about 2e-16 in most
987 cases.
988 full : bool, optional
989 Switch determining nature of return value. When it is False
990 (the default) just the coefficients are returned, when True
991 diagnostic information from the singular value decomposition is
992 also returned.
993 w : array_like, shape (M,), optional
994 Weights. If not None, the weight ``w[i]`` applies to the unsquared
995 residual ``y[i] - y_hat[i]`` at ``x[i]``. Ideally the weights are
996 chosen so that the errors of the products ``w[i]*y[i]`` all have
997 the same variance. When using inverse-variance weighting, use
998 ``w[i] = 1/sigma(y[i])``. The default value is None.
999
1000 .. versionadded:: 1.5.0
1001 window : {[beg, end]}, optional
1002 Window to use for the returned series. The default
1003 value is the default class domain
1004
1005 .. versionadded:: 1.6.0
1006 symbol : str, optional
1007 Symbol representing the independent variable. Default is 'x'.
1008
1009 Returns
1010 -------
1011 new_series : series
1012 A series that represents the least squares fit to the data and
1013 has the domain and window specified in the call. If the

Callers 3

test_bad_conditioned_fitFunction · 0.80
test_fitFunction · 0.80
test_fitFunction · 0.80

Calls 1

_fitMethod · 0.80

Tested by 3

test_bad_conditioned_fitFunction · 0.64
test_fitFunction · 0.64
test_fitFunction · 0.64