# being a bit too dynamic
# pylint: disable=E1101
from __future__ import division

import numpy as np

from pandas.compat import lmap, lrange, range, zip
from pandas.util._decorators import deprecate_kwarg

from pandas.core.dtypes.missing import notna

from pandas.io.formats.printing import pprint_thing
from pandas.plotting._style import _get_standard_colors
from pandas.plotting._tools import _set_ticks_props, _subplots


def scatter_matrix(frame, alpha=0.5, figsize=None, ax=None, grid=False,
                   diagonal='hist', marker='.', density_kwds=None,
                   hist_kwds=None, range_padding=0.05, **kwds):
    """
    Draw a matrix of scatter plots.

    Parameters
    ----------
    frame : DataFrame
    alpha : float, optional
        amount of transparency applied
    figsize : (float,float), optional
        a tuple (width, height) in inches
    ax : Matplotlib axis object, optional
    grid : bool, optional
        setting this to True will show the grid
    diagonal : {'hist', 'kde'}
        pick between 'kde' and 'hist' for
        either Kernel Density Estimation or Histogram
        plot in the diagonal
    marker : str, optional
        Matplotlib marker type, default '.'
    hist_kwds : other plotting keyword arguments
        To be passed to hist function
    density_kwds : other plotting keyword arguments
        To be passed to kernel density estimate plot
    range_padding : float, optional
        relative extension of axis range in x and y
        with respect to (x_max - x_min) or (y_max - y_min),
        default 0.05
    kwds : other plotting keyword arguments
        To be passed to scatter function

    Examples
    --------
    >>> df = pd.DataFrame(np.random.randn(1000, 4), columns=['A','B','C','D'])
    >>> scatter_matrix(df, alpha=0.2)
    """

    df = frame._get_numeric_data()
    n = df.columns.size
    naxes = n * n
    fig, axes = _subplots(naxes=naxes, figsize=figsize, ax=ax,
                          squeeze=False)

    # no gaps between subplots
    fig.subplots_adjust(wspace=0, hspace=0)

    mask = notna(df)

    marker = _get_marker_compat(marker)

    hist_kwds = hist_kwds or {}
    density_kwds = density_kwds or {}

    # GH 14855
    kwds.setdefault('edgecolors', 'none')

    boundaries_list = []
    for a in df.columns:
        values = df[a].values[mask[a].values]
        rmin_, rmax_ = np.min(values), np.max(values)
        rdelta_ext = (rmax_ - rmin_) * range_padding / 2.
        boundaries_list.append((rmin_ - rdelta_ext, rmax_ + rdelta_ext))

    for i, a in zip(lrange(n), df.columns):
        for j, b in zip(lrange(n), df.columns):
            ax = axes[i, j]

            if i == j:
                values = df[a].values[mask[a].values]

                # Deal with the diagonal by drawing a histogram there.
                if diagonal == 'hist':
                    ax.hist(values, **hist_kwds)

                elif diagonal in ('kde', 'density'):
                    from scipy.stats import gaussian_kde
                    y = values
                    gkde = gaussian_kde(y)
                    ind = np.linspace(y.min(), y.max(), 1000)
                    ax.plot(ind, gkde.evaluate(ind), **density_kwds)

                ax.set_xlim(boundaries_list[i])

            else:
                common = (mask[a] & mask[b]).values

                ax.scatter(df[b][common], df[a][common],
                           marker=marker, alpha=alpha, **kwds)

                ax.set_xlim(boundaries_list[j])
                ax.set_ylim(boundaries_list[i])

            ax.set_xlabel(b)
            ax.set_ylabel(a)

            if j != 0:
                ax.yaxis.set_visible(False)
            if i != n - 1:
                ax.xaxis.set_visible(False)

    if len(df.columns) > 1:
        lim1 = boundaries_list[0]
        locs = axes[0][1].yaxis.get_majorticklocs()
        locs = locs[(lim1[0] <= locs) & (locs <= lim1[1])]
        adj = (locs - lim1[0]) / (lim1[1] - lim1[0])

        lim0 = axes[0][0].get_ylim()
        adj = adj * (lim0[1] - lim0[0]) + lim0[0]
        axes[0][0].yaxis.set_ticks(adj)

        if np.all(locs == locs.astype(int)):
            # if all ticks are int
            locs = locs.astype(int)
        axes[0][0].yaxis.set_ticklabels(locs)

    _set_ticks_props(axes, xlabelsize=8, xrot=90, ylabelsize=8, yrot=0)

    return axes


def _get_marker_compat(marker):
    import matplotlib.lines as mlines
    if marker not in mlines.lineMarkers:
        return 'o'
    return marker


def radviz(frame, class_column, ax=None, color=None, colormap=None, **kwds):
    """
    Plot a multidimensional dataset in 2D.

    Each Series in the DataFrame is represented as a evenly distributed
    slice on a circle. Each data point is rendered in the circle according to
    the value on each Series. Highly correlated `Series` in the `DataFrame`
    are placed closer on the unit circle.

    RadViz allow to project a N-dimensional data set into a 2D space where the
    influence of each dimension can be interpreted as a balance between the
    influence of all dimensions.

    More info available at the `original article
    <http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.135.889>`_
    describing RadViz.

    Parameters
    ----------
    frame : `DataFrame`
        Pandas object holding the data.
    class_column : str
        Column name containing the name of the data point category.
    ax : :class:`matplotlib.axes.Axes`, optional
        A plot instance to which to add the information.
    color : list[str] or tuple[str], optional
        Assign a color to each category. Example: ['blue', 'green'].
    colormap : str or :class:`matplotlib.colors.Colormap`, default None
        Colormap to select colors from. If string, load colormap with that
        name from matplotlib.
    kwds : optional
        Options to pass to matplotlib scatter plotting method.

    Returns
    -------
    axes : :class:`matplotlib.axes.Axes`

    See Also
    --------
    pandas.plotting.andrews_curves : Plot clustering visualization.

    Examples
    --------
    .. plot::
        :context: close-figs

        >>> df = pd.DataFrame({
        ...         'SepalLength': [6.5, 7.7, 5.1, 5.8, 7.6, 5.0, 5.4, 4.6,
        ...                         6.7, 4.6],
        ...         'SepalWidth': [3.0, 3.8, 3.8, 2.7, 3.0, 2.3, 3.0, 3.2,
        ...                        3.3, 3.6],
        ...         'PetalLength': [5.5, 6.7, 1.9, 5.1, 6.6, 3.3, 4.5, 1.4,
        ...                         5.7, 1.0],
        ...         'PetalWidth': [1.8, 2.2, 0.4, 1.9, 2.1, 1.0, 1.5, 0.2,
        ...                        2.1, 0.2],
        ...         'Category': ['virginica', 'virginica', 'setosa',
        ...                      'virginica', 'virginica', 'versicolor',
        ...                      'versicolor', 'setosa', 'virginica',
        ...                      'setosa']
        ...     })
        >>> rad_viz = pd.plotting.radviz(df, 'Category')  # doctest: +SKIP
    """
    import matplotlib.pyplot as plt
    import matplotlib.patches as patches

    def normalize(series):
        a = min(series)
        b = max(series)
        return (series - a) / (b - a)

    n = len(frame)
    classes = frame[class_column].drop_duplicates()
    class_col = frame[class_column]
    df = frame.drop(class_column, axis=1).apply(normalize)

    if ax is None:
        ax = plt.gca(xlim=[-1, 1], ylim=[-1, 1])

    to_plot = {}
    colors = _get_standard_colors(num_colors=len(classes), colormap=colormap,
                                  color_type='random', color=color)

    for kls in classes:
        to_plot[kls] = [[], []]

    m = len(frame.columns) - 1
    s = np.array([(np.cos(t), np.sin(t))
                  for t in [2.0 * np.pi * (i / float(m))
                            for i in range(m)]])

    for i in range(n):
        row = df.iloc[i].values
        row_ = np.repeat(np.expand_dims(row, axis=1), 2, axis=1)
        y = (s * row_).sum(axis=0) / row.sum()
        kls = class_col.iat[i]
        to_plot[kls][0].append(y[0])
        to_plot[kls][1].append(y[1])

    for i, kls in enumerate(classes):
        ax.scatter(to_plot[kls][0], to_plot[kls][1], color=colors[i],
                   label=pprint_thing(kls), **kwds)
    ax.legend()

    ax.add_patch(patches.Circle((0.0, 0.0), radius=1.0, facecolor='none'))

    for xy, name in zip(s, df.columns):

        ax.add_patch(patches.Circle(xy, radius=0.025, facecolor='gray'))

        if xy[0] < 0.0 and xy[1] < 0.0:
            ax.text(xy[0] - 0.025, xy[1] - 0.025, name,
                    ha='right', va='top', size='small')
        elif xy[0] < 0.0 and xy[1] >= 0.0:
            ax.text(xy[0] - 0.025, xy[1] + 0.025, name,
                    ha='right', va='bottom', size='small')
        elif xy[0] >= 0.0 and xy[1] < 0.0:
            ax.text(xy[0] + 0.025, xy[1] - 0.025, name,
                    ha='left', va='top', size='small')
        elif xy[0] >= 0.0 and xy[1] >= 0.0:
            ax.text(xy[0] + 0.025, xy[1] + 0.025, name,
                    ha='left', va='bottom', size='small')

    ax.axis('equal')
    return ax


@deprecate_kwarg(old_arg_name='data', new_arg_name='frame')
def andrews_curves(frame, class_column, ax=None, samples=200, color=None,
                   colormap=None, **kwds):
    """
    Generates a matplotlib plot of Andrews curves, for visualising clusters of
    multivariate data.

    Andrews curves have the functional form:

    f(t) = x_1/sqrt(2) + x_2 sin(t) + x_3 cos(t) +
           x_4 sin(2t) + x_5 cos(2t) + ...

    Where x coefficients correspond to the values of each dimension and t is
    linearly spaced between -pi and +pi. Each row of frame then corresponds to
    a single curve.

    Parameters
    ----------
    frame : 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
    color : list or tuple, optional
        Colors to use for the different classes
    colormap : str or matplotlib colormap object, default None
        Colormap to select colors from. If string, load colormap with that name
        from matplotlib.
    kwds : keywords
        Options to pass to matplotlib plotting method

    Returns
    -------
    ax : Matplotlib axis object

    """
    from math import sqrt, pi
    import matplotlib.pyplot as plt

    def function(amplitudes):
        def f(t):
            x1 = amplitudes[0]
            result = x1 / sqrt(2.0)

            # Take the rest of the coefficients and resize them
            # appropriately. Take a copy of amplitudes as otherwise numpy
            # deletes the element from amplitudes itself.
            coeffs = np.delete(np.copy(amplitudes), 0)
            coeffs.resize(int((coeffs.size + 1) / 2), 2)

            # Generate the harmonics and arguments for the sin and cos
            # functions.
            harmonics = np.arange(0, coeffs.shape[0]) + 1
            trig_args = np.outer(harmonics, t)

            result += np.sum(coeffs[:, 0, np.newaxis] * np.sin(trig_args) +
                             coeffs[:, 1, np.newaxis] * np.cos(trig_args),
                             axis=0)
            return result
        return f

    n = len(frame)
    class_col = frame[class_column]
    classes = frame[class_column].drop_duplicates()
    df = frame.drop(class_column, axis=1)
    t = np.linspace(-pi, pi, samples)
    used_legends = set()

    color_values = _get_standard_colors(num_colors=len(classes),
                                        colormap=colormap, color_type='random',
                                        color=color)
    colors = dict(zip(classes, color_values))
    if ax is None:
        ax = plt.gca(xlim=(-pi, pi))