Merge pull request #3422 from karmel/master

DOC: Adding parameters address issue sub-points 8 and 10 - 24 (issue #2916)

Author: y-p

pandas/core/reshape.py

@@ -745,11 +745,13 @@ def make_axis_dummies(frame, axis='minor', transform=None):
 
     Parameters
     ----------
+    frame : DataFrame
     axis : {'major', 'minor'}, default 'minor'
     transform : function, default None
         Function to apply to axis labels first. For example, to
-        get "day of week" dummies in a time series regression you might
-        call:
+        get "day of week" dummies in a time series regression 
+        you might call::
+            
             make_axis_dummies(panel, axis='major',
                               transform=lambda d: d.weekday())
     Returns

pandas/stats/math.py

@@ -50,13 +50,14 @@ def newey_west(m, max_lags, nobs, df, nw_overlap=False):
 
     Parameters
     ----------
-    m: (N x K)
-    max_lags: int
-    nobs: int
+    m : (N x K)
+    max_lags : int
+    nobs : int
         Number of observations in model
-    df: int
+    df : int
         Degrees of freedom in explanatory variables
-    nw_overlap: boolean
+    nw_overlap : boolean, default False
+        Assume data is overlapping
 
     Returns
     -------

pandas/stats/moments.py

@@ -137,7 +137,8 @@ def rolling_count(arg, window, freq=None, center=False, time_rule=None):
         Frequency to conform to before computing statistic
     center : boolean, default False
         Whether the label should correspond with center of window
-
+    time_rule : Legacy alias for freq
+    
     Returns
     -------
     rolling_count : type of caller
@@ -268,7 +269,8 @@ def _rolling_moment(arg, window, func, minp, axis=0, freq=None,
         Frequency to conform to before computing statistic
     center : boolean, default False
         Whether the label should correspond with center of window
-
+    time_rule : Legacy alias for freq
+    
     Returns
     -------
     y : type of input
@@ -540,7 +542,8 @@ def rolling_quantile(arg, window, quantile, min_periods=None, freq=None,
         Frequency to conform to before computing statistic
     center : boolean, default False
         Whether the label should correspond with center of window
-
+    time_rule : Legacy alias for freq
+    
     Returns
     -------
     y : type of input argument
@@ -569,7 +572,8 @@ def rolling_apply(arg, window, func, min_periods=None, freq=None,
         Frequency to conform to before computing statistic
     center : boolean, default False
         Whether the label should correspond with center of window
-
+    time_rule : Legacy alias for freq
+    
     Returns
     -------
     y : type of input argument
@@ -604,7 +608,9 @@ def rolling_window(arg, window=None, win_type=None, min_periods=None,
         Whether the label should correspond with center of window
     mean : boolean, default True
         If True computes weighted mean, else weighted sum
-
+    time_rule : Legacy alias for freq
+    axis : {0, 1}, default 0
+    
     Returns
     -------
     y : type of input argument
@@ -729,7 +735,8 @@ def expanding_count(arg, freq=None, center=False, time_rule=None):
         Frequency to conform to before computing statistic
     center : boolean, default False
         Whether the label should correspond with center of window
-
+    time_rule : Legacy alias for freq
+    
     Returns
     -------
     expanding_count : type of caller
@@ -752,7 +759,8 @@ def expanding_quantile(arg, quantile, min_periods=1, freq=None,
         Frequency to conform to before computing statistic
     center : boolean, default False
         Whether the label should correspond with center of window
-
+    time_rule : Legacy alias for freq
+    
     Returns
     -------
     y : type of input argument
@@ -816,7 +824,8 @@ def expanding_apply(arg, func, min_periods=1, freq=None, center=False,
         Frequency to conform to before computing statistic
     center : boolean, default False
         Whether the label should correspond with center of window
-
+    time_rule : Legacy alias for freq
+    
     Returns
     -------
     y : type of input argument

pandas/stats/ols.py

@@ -28,12 +28,19 @@ class OLS(object):
 
     Parameters
     ----------
-    y: Series
-    x: Series, DataFrame, dict of Series
-    intercept: bool
+    y : Series
+    x : Series, DataFrame, dict of Series
+    intercept : bool
         True if you want an intercept.
-    nw_lags: None or int
+    weights : array-like, optional
+        1d array of weights.  If you supply 1/W then the variables are pre-
+        multiplied by 1/sqrt(W).  If no weights are supplied the default value
+        is 1 and WLS reults are the same as OLS.
+    nw_lags : None or int
         Number of Newey-West lags.
+    nw_overlap : boolean, default False
+        Assume data is overlapping when computing Newey-West estimator
+    
     """
     _panel_model = False
 
@@ -593,16 +600,24 @@ class MovingOLS(OLS):
 
     Parameters
     ----------
-    y: Series
-    x: Series, DataFrame, or dict of Series
-    intercept: bool
-        True if you want an intercept.
-    nw_lags: None or int
-        Number of Newey-West lags.
-    window_type: {'full sample', 'rolling', 'expanding'}
+    y : Series
+    x : Series, DataFrame, or dict of Series
+    weights : array-like, optional
+        1d array of weights.  If None, equivalent to an unweighted OLS.
+    window_type : {'full sample', 'rolling', 'expanding'}
         Default expanding
-    window: int
+    window : int
         size of window (for rolling/expanding OLS)
+    min_periods : int
+        Threshold of non-null data points to require. 
+        If None, defaults to size of window. 
+    intercept : bool
+        True if you want an intercept.
+    nw_lags : None or int
+        Number of Newey-West lags.
+    nw_overlap : boolean, default False
+        Assume data is overlapping when computing Newey-West estimator
+    
     """
     def __init__(self, y, x, weights=None, window_type='expanding',
                  window=None, min_periods=None, intercept=True,
@@ -1248,10 +1263,12 @@ def _filter_data(lhs, rhs, weights=None):
 
     Parameters
     ----------
-    lhs: Series
+    lhs : Series
         Dependent variable in the regression.
-    rhs: dict, whose values are Series, DataFrame, or dict
+    rhs : dict, whose values are Series, DataFrame, or dict
         Explanatory variables of the regression.
+    weights : array-like, optional
+        1d array of weights.  If None, equivalent to an unweighted OLS.
 
     Returns
     -------

pandas/tools/plotting.py

@@ -165,13 +165,15 @@ def scatter_matrix(frame, alpha=0.5, figsize=None, ax=None, grid=False,
 
     Parameters
     ----------
+    frame : DataFrame
     alpha : amount of transparency applied
     figsize : a tuple (width, height) in inches
     ax : Matplotlib axis object
     grid : setting this to True will show the grid
     diagonal : pick between 'kde' and 'hist' for
         either Kernel Density Estimation or Histogram
         plot in the diagonal
+    marker : Matplotlib marker type, default '.'
     kwds : other plotting keyword arguments
         To be passed to scatter function
 
@@ -365,10 +367,17 @@ def normalize(series):
 def andrews_curves(data, class_column, ax=None, samples=200):
     """
     Parameters:
-    data: A DataFrame containing data to be plotted, preferably
-    normalized to (0.0, 1.0).
-    class_column: Name of the column containing class names.
-    samples: Number of points to plot in each curve.
+    -----------
+    data : DataFrame 
+        Data to be plotted, preferably normalized to (0.0, 1.0)
+    class_column : Name of the column containing class names
+    ax : matplotlib axes object, default None
+    samples : Number of points to plot in each curve
+    
+    Returns:
+    --------
+    ax: Matplotlib axis object
+    
     """
     from math import sqrt, pi, sin, cos
     import matplotlib.pyplot as plt
@@ -1475,6 +1484,7 @@ def plot_frame(frame=None, x=None, y=None, subplots=False, sharex=True,
 
     Parameters
     ----------
+    frame : DataFrame
     x : label or position, default None
     y : label or position, default None
         Allows plotting of one column versus another
@@ -1675,8 +1685,11 @@ def boxplot(data, column=None, by=None, ax=None, fontsize=None,
         Can be any valid input to groupby
     by : string or sequence
         Column in the DataFrame to group by
+    ax : Matplotlib axis object, optional
     fontsize : int or string
     rot : label rotation angle
+    figsize : A tuple (width, height) in inches
+    grid : Setting this to True will show the grid
     kwds : other plotting keyword arguments to be passed to matplotlib boxplot
            function
 
@@ -1779,7 +1792,19 @@ def format_date_labels(ax, rot):
 
 def scatter_plot(data, x, y, by=None, ax=None, figsize=None, grid=False, **kwargs):
     """
+    Make a scatter plot from two DataFrame columns
 
+    Parameters
+    ----------
+    data : DataFrame
+    x : Column name for the x-axis values
+    y : Column name for the y-axis values
+    ax : Matplotlib axis object
+    figsize : A tuple (width, height) in inches
+    grid : Setting this to True will show the grid
+    kwargs : other plotting keyword arguments
+        To be passed to scatter function
+    
     Returns
     -------
     fig : matplotlib.Figure
@@ -1818,6 +1843,11 @@ def hist_frame(
 
     Parameters
     ----------
+    data : DataFrame
+    column : string or sequence
+        If passed, will be used to limit data to a subset of columns
+    by : object, optional
+        If passed, then used to form histograms for separate groups
     grid : boolean, default True
         Whether to show axis grid lines
     xlabelsize : int, default None
@@ -1956,13 +1986,16 @@ def boxplot_frame_groupby(grouped, subplots=True, column=None, fontsize=None,
 
     Parameters
     ----------
+    grouped : Grouped DataFrame
     subplots :
         * ``False`` - no subplots will be used
         * ``True`` - create a subplot for each group
     column : column name or list of names, or vector
         Can be any valid input to groupby
     fontsize : int or string
     rot : label rotation angle
+    grid : Setting this to True will show the grid
+    figsize : A tuple (width, height) in inches
     kwds : other plotting keyword arguments to be passed to matplotlib boxplot
            function
 
@@ -2157,15 +2190,19 @@ def _subplots(nrows=1, ncols=1, sharex=False, sharey=False, squeeze=True,
       Dict with keywords passed to the add_subplot() call used to create each
       subplots.
 
-    fig_kw : dict
-      Dict with keywords passed to the figure() call.  Note that all keywords
-      not recognized above will be automatically included here.
-
-    ax : Matplotlib axis object, default None
+    ax : Matplotlib axis object, optional
 
     secondary_y : boolean or sequence of ints, default False
         If True then y-axis will be on the right
 
+    data : DataFrame, optional
+        If secondary_y is a sequence, data is used to select columns.
+     
+    fig_kw : Other keyword arguments to be passed to the figure() call.  
+        Note that all keywords not recognized above will be 
+        automatically included here.
+
+
     Returns:
 
     fig, ax : tuple