DOC: Correct spacing around colon in docstrings

Ensure that param : type is correctly spaced

statsmodels/discrete/count_model.py

@@ -47,7 +47,7 @@ class GenericZeroInflated(CountModel):
         A reference to the endogenous response variable
     exog : ndarray
         A reference to the exogenous design.
-    exog_infl: ndarray
+    exog_infl : ndarray
         A reference to the zero-inflated exogenous design.
     """ % {'params' : base._model_params_doc,
            'extra_params' : _doc_zi_params + base._missing_param_doc}
@@ -466,7 +466,7 @@ class ZeroInflatedPoisson(GenericZeroInflated):
         A reference to the endogenous response variable
     exog : ndarray
         A reference to the exogenous design.
-    exog_infl: ndarray
+    exog_infl : ndarray
         A reference to the zero-inflated exogenous design.
     """ % {'params' : base._model_params_doc,
            'extra_params' : _doc_zi_params + base._missing_param_doc}
@@ -554,9 +554,9 @@ class ZeroInflatedGeneralizedPoisson(GenericZeroInflated):
         A reference to the endogenous response variable
     exog : ndarray
         A reference to the exogenous design.
-    exog_infl: ndarray
+    exog_infl : ndarray
         A reference to the zero-inflated exogenous design.
-    p: scalar
+    p : scalar
         P denotes parametrizations for ZIGP regression.
     """ % {'params' : base._model_params_doc,
            'extra_params' : _doc_zi_params +
@@ -632,9 +632,9 @@ class ZeroInflatedNegativeBinomialP(GenericZeroInflated):
         A reference to the endogenous response variable
     exog : ndarray
         A reference to the exogenous design.
-    exog_infl: ndarray
+    exog_infl : ndarray
         A reference to the zero-inflated exogenous design.
-    p: scalar
+    p : scalar
         P denotes parametrizations for ZINB regression. p=1 for ZINB-1 and
     p=2 for ZINB-2. Default is p=2
     """ % {'params' : base._model_params_doc,

statsmodels/distributions/edgeworth.py

@@ -21,20 +21,21 @@
 
 
 def _faa_di_bruno_partitions(n):
-    """ Return all non-negative integer solutions of the diophantine equation
+    """
+    Return all non-negative integer solutions of the diophantine equation
 
             n*k_n + ... + 2*k_2 + 1*k_1 = n   (1)
 
     Parameters
     ----------
-    n: int
+    n : int
         the r.h.s. of Eq. (1)
 
     Returns
     -------
-    partitions: a list of solutions of (1). Each solution is itself
-        a list of the form `[(m, k_m), ...]` for non-zero `k_m`.
-        Notice that the index `m` is 1-based.
+    partitions : list
+        Each solution is itself a list of the form `[(m, k_m), ...]`
+        for non-zero `k_m`. Notice that the index `m` is 1-based.
 
     Examples:
     ---------
@@ -58,16 +59,16 @@ def cumulant_from_moments(momt, n):
 
     Parameters
     ----------
-    momt: array_like
+    momt : array_like
         `momt[j]` contains `(j+1)`-th moment.
         These can be raw moments around zero, or central moments
         (in which case, `momt[0]` == 0).
-    n: int
+    n : int
         which cumulant to calculate (must be >1)
 
     Returns
     -------
-    kappa: float
+    kappa : float
         n-th cumulant.
     """
     if n < 1:
@@ -103,7 +104,7 @@ class ExpandedNormal(rv_continuous):
 
     Parameters
     ----------
-    cum: array_like
+    cum : array_like
         `cum[j]` contains `(j+1)`-th cumulant: cum[0] is the mean,
         cum[1] is the variance and so on.
 

statsmodels/emplike/aft_el.py

@@ -70,8 +70,7 @@ def _opt_wtd_nuis_regress(self, test_vals):
 
         Returns
         -------
-
-        llr: float
+        llr : float
             -2 times the log likelihood of the nuisance parameters and the
             hypothesized value of the parameter(s) of interest.
         """
@@ -95,10 +94,10 @@ def _EM_test(self, nuisance_params, params=None, param_nums=None,
         Parameters
         ----------
 
-        Nuisance Params: ndarray
+        nuisance_params : ndarray
             Vector of values to be used as nuisance params.
 
-        maxiter: int
+        maxiter : int
             Number of iterations in the EM algorithm for a parameter vector
 
         Returns
@@ -160,8 +159,7 @@ def _ci_limits_beta(self, b0, param_num=None):
         ----------
         b0: float
             Value of a regression parameter
-
-        param_num: int
+        param_num : int
             Parameter index of b0
         """
         return self.test_beta([b0], [param_num])[0] - self.r0
@@ -187,29 +185,21 @@ class emplikeAFT(object):
 
     Attributes
     ----------
-
-    nobs: float
+    nobs : float
         Number of observations
-
-    endog: ndarray
+    endog : ndarray
         Endog attay
-
-    exog: ndarray
+    exog : ndarray
         Exogenous variable matrix
-
     censors
         Censors array but sets the max(endog) to uncensored
-
-    nvar: float
+    nvar : float
         Number of exogenous variables
-
-    uncens_nobs: float
+    uncens_nobs : float
         Number of uncensored observations
-
-    uncens_endog: ndarray
+    uncens_endog : ndarray
         Uncensored response variables
-
-    uncens_exog: ndarray
+    uncens_exog : ndarray
         Exogenous variables of the uncensored observations
 
     Methods
@@ -254,14 +244,14 @@ def _is_tied(self, endog, censors):
 
         Parameters
         ----------
-        endog: ndarray
+        endog : ndarray
             Models endogenous variable
-        censors: ndarray
+        censors : ndarray
             arrat indicating a censored array
 
         Returns
         -------
-        indic_ties: ndarray
+        indic_ties : ndarray
             ties[i]=1 if endog[i]==endog[i+1] and
             censors[i]=censors[i+1]
         """
@@ -398,20 +388,16 @@ def test_beta(self, b0_vals, param_nums, ftol=10 ** - 5, maxiter=30,
 
         Parameters
         ----------
-        b0_vals: list
+        b0_vals : list
             The value of parameters to be tested
-
-        param_num: list
+        param_num : list
             Which parameters to be tested
-
-        maxiter: int, optional
+        maxiter : int, optional
             How many iterations to use in the EM algorithm.  Default is 30
-
-        ftol: float, optional
+        ftol : float, optional
             The function tolerance for the EM optimization.
             Default is 10''**''-5
-
-        print_weights: bool
+        print_weights : bool
             If true, returns the weights tate maximize the profile
             log likelihood. Default is False
 
@@ -507,17 +493,13 @@ def ci_beta(self, param_num, beta_high, beta_low, sig=.05):
 
         Parameters
         ----------
-
-        param_num: int
+        param_num : int
             Parameter number of interest
-
-        beta_high: float
+        beta_high : float
             Upper bound for the confidence interval
-
-        beta_low:
+        beta_low : float
             Lower bound for the confidence interval
-
-        sig: float, optional
+        sig : float, optional
             Significance level.  Default is .05
 
         Notes

statsmodels/gam/gam_penalties.py

@@ -137,7 +137,7 @@ class MultivariateGamPenalty(Penalty):
     alpha : list of float
         default penalty weight, list with length equal to the number of smooth
         terms. ``alpha`` can also be provided to each method.
-    weights: array_like
+    weights : array_like
         currently not used
         is a list of doubles of the same length as alpha or a list
         of ndarrays where each component has the length equal to the number

statsmodels/gam/smooth_basis.py

@@ -668,10 +668,16 @@ def _get_b_and_d(self, knots):
 
         Returns
         -------
-        b, d: ndarrays
-            arrays for mapping cyclic cubic spline values at knots to
+        b : ndarray
+            Array for mapping cyclic cubic spline values at knots to
             second derivatives.
-            penalty matrix is equal to ``s = d.T.dot(b^-1).dot(d)``
+        d : ndarray
+            Array for mapping cyclic cubic spline values at knots to
+            second derivatives.
+
+        Notes
+        -----
+        The penalty matrix is equal to ``s = d.T.dot(b^-1).dot(d)``
         """
         h = knots[1:] - knots[:-1]
         n = knots.size - 1

statsmodels/genmod/cov_struct.py

@@ -79,18 +79,18 @@ def covariance_matrix(self, endog_expval, index):
 
         Parameters
         ----------
-        endog_expval: array_like
+        endog_expval : array_like
            The expected values of endog for the cluster for which the
            covariance or correlation matrix will be returned
-        index: int
+        index : int
            The index of the cluster for which the covariance or
            correlation matrix will be returned
 
         Returns
         -------
-        M: matrix
+        M : matrix
             The covariance or correlation matrix of endog
-        is_cor: bool
+        is_cor : bool
             True if M is a correlation matrix, False if M is a
             covariance matrix
         """
@@ -104,10 +104,10 @@ def covariance_matrix_solve(self, expval, index, stdev, rhs):
 
         Parameters
         ----------
-        expval: array_like
+        expval : array_like
            The expected value of endog for each observed value in the
            group.
-        index: int
+        index : int
            The group index.
         stdev : array_like
             The standard deviation of endog for each observation in

statsmodels/genmod/families/links.py

@@ -194,7 +194,7 @@ def deriv(self, p):
 
         Parameters
         ----------
-        p: array_like
+        p : array_like
             Probabilities
 
         Returns
@@ -731,7 +731,7 @@ def deriv2(self, p):
 
         Parameters
         ----------
-        p: array_like
+        p : array_like
             Probabilities
 
         Returns

statsmodels/iolib/summary2.py

@@ -38,9 +38,9 @@ def add_df(self, df, index=True, header=True, float_format='%.4f',
         Parameters
         ----------
         df : DataFrame
-        header: bool
+        header : bool
             Reproduce the DataFrame column labels in summary table
-        index: bool
+        index : bool
             Reproduce the DataFrame row labels in summary table
         float_format : str
             Formatting to float data columns
@@ -77,7 +77,7 @@ def add_dict(self, d, ncols=2, align='l', float_format="%.4f"):
         d : dict
             Keys and values are automatically coerced to strings with str().
             Users are encouraged to format them before using add_dict.
-        ncols: int
+        ncols : int
             Number of columns of the output table
         align : str
             Data alignment (l/c/r)

statsmodels/multivariate/cancorr.py

@@ -34,9 +34,9 @@ class CanCorr(Model):
         See Parameters.
     cancorr : ndarray
         The canonical correlation values
-    y_cancoeff: ndarray
+    y_cancoeff : ndarray
         The canonical coefficients for endog
-    x_cancoeff: ndarray
+    x_cancoeff : ndarray
         The canonical coefficients for exog
 
     References

statsmodels/multivariate/factor.py

@@ -501,10 +501,10 @@ class FactorResults(object):
 
     Attributes
     ----------
-    uniqueness: ndarray
+    uniqueness : ndarray
         The uniqueness (variance of uncorrelated errors unique to
         each variable)
-    communality: ndarray
+    communality : ndarray
         1 - uniqueness
     loadings : ndarray
         Each column is the loading vector for one factor
@@ -979,7 +979,7 @@ def uniq_stderr(self, kurt=0):
 
         Parameters
         ----------
-        kurt: float
+        kurt : float
             Excess kurtosis
 
         Notes