a Sic߸@sdZddlZddlZddlmZddlmZddlm Z ddl Z ddl Z zddlmZdZWneyrdZYn0dd lmZdd lmZdd lmZdd lmZmZmZmZmZd dgZddZddZ ddZ!ddZ"GdddZ#ddddddddddddddddddddd Z$GdddZ%dddd d!dddd"d#d$Z&Gd%d&d&eZ'dd!d ddd'ddddddddd(d)d*dd+d,dZ(dS)-z(Functions to visualize matrices of data.N)LineCollection)gridspec) hierarchyFT)cm)Grid) get_colormap)despineaxis_ticklabels_overlaprelative_luminanceto_utf8 _draw_figureheatmap clustermapcCs(t|tjrdtt|jS|jSdS)z6Convert a pandas index or multiindex to an axis label.-N) isinstancepd MultiIndexjoinmapr namesnameindexrJ/var/www/html/django/DPS/env/lib/python3.9/site-packages/seaborn/matrix.py_index_to_labels rcCs&t|tjrdd|jDS|jSdS)z5Convert a pandas index or multiindex into ticklabels.cSsg|]}dtt|qS)r)rrr .0irrr *z(_index_to_ticklabels..N)rrrvaluesrrrr_index_to_ticklabels's r#csNtjjz|dtt|WStyHfdd|DYS0dS)zAConvert either a list of colors or nested lists of colors to RGB.rcsg|]}tt|qSr)listr)rlto_rgbrrr 9r!z#_convert_colors..N)mplcolorsr'r$r ValueError)r)rr&r_convert_colors/s   r+cCs|durt|jt}t|tjrN|j|jkr6tdtj||j |j td}n4t|tjr|j |j s|j |j rd}t||t |B}|S)zEnsure that data and mask are compatible and add missing values. Values will be plotted for cells where ``mask`` is ``False``. ``data`` is expected to be a DataFrame; ``mask`` can be an array or a DataFrame. Nz&Mask must have the same shape as data.)rcolumnsdtypez2Mask must have the same index and columns as data.) npzerosshapeboolrndarrayr*r DataFramerr,equalsisnull)datamaskerrrrr _matrix_mask<s$     r9c@sBeZdZdZdddZddZdd Zd d Zd d ZddZ dS) _HeatMapperz?Draw a heatmap plot of a matrix with nice labels and colormaps.TNcCsht|tjr|j}nt|}t|}t||}tjt||}d}t| t rd| }t |j } n | durxt |j } n | durg} d}t| t r| }t |j } n | durt |j } n | durg} t | sg|_g|_n:t| tr| dkrd|_t |j |_n|| |\|_|_t | s*g|_g|_n>t| trT| dkrTd|_t |j |_n|| |\|_|_t|j }t|j }|dur|nd|_|dur|nd|_||||||||dus|durd}d}n:t|tr|}n$t|}|j|jkr d}t|d}||_||_||_||_||_| dur.r<)r<r<ZdcoordZicoord) rTrrr3r"r.r>arrayr6r0metricmethodlabelrotatecalculated_linkagelinkagecalculate_dendrogram dendrogramrr#r reordered_indrCrGrDrHrrJrIdependent_coordindependent_coord) rTr6rrrrrrrrrrrrZsR          z_DendrogramPlotter.__init__cCstj|j|j|jd}|S)Nrr)rrrrr)rTrrrr_calculate_linkage_scipys z+_DendrogramPlotter._calculate_linkage_scipycCsbddl}d}|jdko|j|v}|s.|jdkrD|j|j|j|jdS|j|j|j|jd}|SdS)Nr)centroidmedianZward euclideansingler) fastclusterrrZlinkage_vectorrr)rTrZeuclidean_methodsrrrrr_calculate_linkage_fastclusters z1_DendrogramPlotter._calculate_linkage_fastclustercCsDz |WSty:t|jdkr6d}t|Yn0|S)Ni'zYClustering large matrix with scipy. Installing `fastcluster` may give better performance.)r ImportErrorr.productr0warningswarnr)rTmsgrrrr's  z%_DendrogramPlotter.calculated_linkagecCstj|jdtj dS)aCalculates a dendrogram based on the linkage matrix Made a separate function, not a property because don't want to recalculate the dendrogram every time it is accessed. Returns ------- dendrogram : dict Dendrogram dictionary as returned by scipy.cluster.hierarchy .dendrogram. The important key-value pairing is "reordered_ind" which indicates the re-ordering of the matrix T)Zno_plotZcolor_threshold)rrrr.rhrTrrrr4s z'_DendrogramPlotter.calculate_dendrogramcCs |jdS)z2Indices of the matrix, reordered by the dendrogramleaves)rrrrrrDsz _DendrogramPlotter.reordered_indc Cs|dur in|}|dd|d|dd|jrT|jdkrTt|j|j}nt|j|j}tdd |Dfi|}| |t |j }t t t |j}|jr|jd |d|d |d|d ||n |d|d |d|d t|d d d|j|j|j|j|jd||j}|j|jdd}t|jt |dkrxt |rxt!j"|ddt |dkrt |rt!j"|dd|S)zPlots a dendrogram of the similarities between data on the axes Parameters ---------- ax : matplotlib.axes.Axes Axes object upon which the dendrogram is plotted Nrrwr)rz)皙?rrrcSsg|]\}}tt||qSr)r$r)rrrrrrr Zr!z+_DendrogramPlotter.plot..rightrg?Trrr)rCrGrIrJrrr)#rPrpoprrrrrradd_collectionrBrrjrrset_ticks_positionset_ylimset_xlim invert_xaxisrr rrCrGrIrJrrDrrHr rr rr) rTrtree_kwscoordslinesZnumber_of_leavesZmax_dependent_coordrrrrrrIs@         z_DendrogramPlotter.plotN) rrrrrZrrpropertyrrrrrrrrrs?  rraverage)rrrrrrrrc Cs@tr tdt|||||||d} |dur2t}| j||dS)aDraw a tree diagram of relationships within a matrix Parameters ---------- data : pandas.DataFrame Rectangular data linkage : numpy.array, optional Linkage matrix axis : int, optional Which axis to use to calculate linkage. 0 is rows, 1 is columns. label : bool, optional If True, label the dendrogram at leaves with column or row names metric : str, optional Distance metric. Anything valid for scipy.spatial.distance.pdist method : str, optional Linkage method to use. Anything valid for scipy.cluster.hierarchy.linkage rotate : bool, optional When plotting the matrix, whether to rotate it 90 degrees counter-clockwise, so the leaves face right tree_kws : dict, optional Keyword arguments for the ``matplotlib.collections.LineCollection`` that is used for plotting the lines of the dendrogram tree. ax : matplotlib axis, optional Axis to plot on, otherwise uses current axis Returns ------- dendrogramplotter : _DendrogramPlotter A Dendrogram plotter object. Notes ----- Access the reordered dendrogram indices with dendrogramplotter.reordered_ind z)dendrogram requires scipy to be installed)rrrrrrN)rr) _no_scipy RuntimeErrorrrrr) r6rrrrrrrrrrrrrs*rc @szeZdZdddZddZdddZedd d Zedd d Zd dZ edddZ ddZ ddZ ddZ ddZdS) ClusterGridNc Cstr tdt|tjr ||_n t||_||j||||_t|j||_ t j |d|_ |j ||dd\|_|_|j ||dd\|_|_z | \} } Wnty| } } Yn0z | \}}Wnty| }}Yn0||j| |}||j| |}|jdur dnd}|jdur dnd}tj||||d |_|j |jd |_|j |jd |_|j|jd|_d|_|jdur|j |jd |_|jdur|j |jd |_|j |jd|_| durd|_|_n|j |jd|_|j|_| |_ d|_!d|_"dS)z=Grid object for organizing clustered heatmap input on to axesz*ClusterGrid requires scipy to be available)figsizerrrNr[) width_ratios height_ratios)r)rr)rr)rr)rr)rr)#r r rrr3r6 format_datadata2dr9r7rr_figure_preprocess_colors row_colorsrow_color_labels col_colorscol_color_labels TypeError dim_ratiosrGridSpecgs add_subplotax_row_dendrogramax_col_dendrogram set_axis_off ax_row_colors ax_col_colors ax_heatmapax_cbarrcbar_posdendrogram_rowdendrogram_col)rTr6 pivot_kwsz_scorestandard_scaler rrr7dendrogram_ratio colors_ratior'Zrow_dendrogram_ratioZcol_dendrogram_ratioZrow_colors_ratioZcol_colors_ratiorrnrowsncolsrrrrZst              zClusterGrid.__init__cCsd}|durt|tjtjfrt|ds0|dksBt|dsf|dkrf|rJdnd}|d|d }t||dkr|||j}n ||j}| t  d }t|tjrt |j}|j j}n |jdurd g}n|jg}|j}t|}||fS) zAPreprocess {row/col}_colors to extract labels and convert colors.Nrrr,rcolrowz<_colors indices can't be matched with data indices. Provide z?_colors as a non-indexed datatype, e.g. by using `.to_numpy()``rr<)rrr3Serieshasattrrreindexrr,r^objectfillnar$rr"rr+)rTr6r)rr axis_namerrrrrs4      zClusterGrid._preprocess_colorscCsb|dur|jfi|}n|}|dur6|dur6td|durJ|||}|dur^|||}|S)z,Extract variables from data or use directly.Nz:Cannot perform both z-scoring and standard-scaling on data)pivotr*r+r,)rTr6r*r+r,rrrrr0s  zClusterGrid.format_datarcCs>|dkr|}n|j}|||}|dkr4|S|jSdS)aStandarize the mean and variance of the data axis Parameters ---------- data2d : pandas.DataFrame Data to normalize axis : int Which axis to normalize across. If 0, normalize across rows, if 1, normalize across columns. Returns ------- normalized : pandas.DataFrame Noramlized data with a mean of 0 and variance of 1 across the specified axis. rN)rmeanstd)rrZz_scoredrrrr+DszClusterGrid.z_scorecCsJ|dkr|}n|j}|}||||}|dkr@|S|jSdS)aDivide the data by the difference between the max and min Parameters ---------- data2d : pandas.DataFrame Data to normalize axis : int Which axis to normalize across. If 0, normalize across rows, if 1, normalize across columns. Returns ------- standardized : pandas.DataFrame Noramlized data with a mean of 0 and variance of 1 across the specified axis. rN)rminrj)rrZ standardizedsubtractrrrr,bszClusterGrid.standard_scalecCsN|g}|dur8t|dkr&t|}nd}|||g7}|dt||S)z8Get the proportions of the figure taken up by each axes.Nr[r)r.ndimrBappendsum)rTr)r-r.ratiosn_colorsrrrrs zClusterGrid.dim_ratiosrc sztj|dWnNtybt|t|d}tfdd|ddDs^tdYn0dt|}|g}i}t|ft}t |D]6\}}t |D]$\}} | | t|} | |||f<qq|dd|f}|dkr|j }tj t |} || fS)aTurns a list of colors into a numpy matrix and matplotlib colormap These arguments can now be plotted using heatmap(matrix, cmap) and the provided colors will be plotted. Parameters ---------- colors : list of matplotlib colors Colors to label the rows or columns of a dataframe. ind : list of ints Ordering of the rows or columns, to reorder the original colors by the clustered dendrogram order axis : int Which axis this is labeling Returns ------- matrix : numpy.array A numpy array of integer values, where each indexes into the cmap cmap : matplotlib.colors.ListedColormap rc3s|]}t|kVqdS)N)rB)rcrrr r!z.rNz/Multiple side color vectors must have same size)r(r)r'r*rBallr.r/rA enumeraterrrfr$) r)indrr unique_colorsmatrixrinnerjrzidxrWrrDrcolor_list_to_matrix_and_cmaps& z)ClusterGrid.color_list_to_matrix_and_cmapc Cs|r&t|j||dd|jd||d |_n|jg|jg|rbt|j||dd|j||d|_n|jg|jgt|jdddt|jddddS)NFrT)rrrrrrrrr)rrrrrrrr) rrr r( set_xticks set_yticksr!r)r )rT row_cluster col_clusterrr row_linkage col_linkagerrrrplot_dendrogramss$        zClusterGrid.plot_dendrogramscKs|}|dd|dd|dd|dd|dd|dd|dd|d d|d d|jdur|j|j|d d \}}|jdur|j}nd }t|f|d |j|d d||d urtj|j ddnt |jddd|j durz|j|j |dd \}}|j dur,|j }nd }t|f|d |j d |d||d ur|j jtj|j d dnt |j ddddS)zPlots color labels between the dendrogram and the heatmap Parameters ---------- heatmap_kws : dict Keyword arguments heatmap rWNrrXrMrUrVrYrDrHrrF)rWrRrrDrHZrT)rrr)rPrrrNrrr#rrget_xticklabelsr rrr$r tick_rightget_yticklabels)rTxindyindrrJrWrrrrr plot_colorssR                  zClusterGrid.plot_colorsc Ks|jj||f|_|jj||f|_|dd}zt||}WnttfyXYn0|dd}zt||}WnttfyYn0|dd}|dus|durnNt|t r|j}n8t|}|j |jj krd} t | ||dd|f}|}| d|j dut|jf|j|j ||j|||d||j}|sJdn |d } |jjd |jjd | dur|j}tj|| d td d d } |j dur|jjfi| n4|j |jjfi| |j |j |jdS)NrDr;rHrMFr=rR)rrrSr7rDrHrMrrr{Gz?)h_padw_pad)rilocr7rr.r>r IndexErrorrr1r0r*rr&rr%rY get_rotationrrset_label_positionrrrr tight_layoutr" set_axis_on set_positionr') rT colorbar_kwsrZr[rrrrMrNr8Zytl_rotZ tight_paramsrrr plot_matrix$sX            zClusterGrid.plot_matrixc Ks| ddr$d} t| | d|dur0in|}|j|||||||dz |jj} Wn$ty|t |j j d} Yn0z |j j} Wn$tyt |j j d} Yn0|j | | fi| |j|| | fi| |S)NrFz%``square=True`` ignored in clustermap)rSrTrrr)rrrrrUr)rAttributeErrorr.rrr0r(r\rh) rTrrrgrQrRrSrTrrrrZr[rrrr]s(        zClusterGrid.plot) NNNNNNNNNN)NN)r)r)r)rrrrZrr staticmethodr+r,rrNrUr\rhrrrrrr s& L*   ! 3A9r )rrrgQ?)r]g?g?g ףp= ?)r*rrr+r,r rSrQrRrSrTrrr7r-r.r'rc KsLtr tdt|||| | ||||||d }|jf||||| | | |d|S)a0 Plot a matrix dataset as a hierarchically-clustered heatmap. This function requires scipy to be available. Parameters ---------- data : 2D array-like Rectangular data for clustering. Cannot contain NAs. pivot_kws : dict, optional If `data` is a tidy dataframe, can provide keyword arguments for pivot to create a rectangular dataframe. method : str, optional Linkage method to use for calculating clusters. See :func:`scipy.cluster.hierarchy.linkage` documentation for more information. metric : str, optional Distance metric to use for the data. See :func:`scipy.spatial.distance.pdist` documentation for more options. To use different metrics (or methods) for rows and columns, you may construct each linkage matrix yourself and provide them as `{row,col}_linkage`. z_score : int or None, optional Either 0 (rows) or 1 (columns). Whether or not to calculate z-scores for the rows or the columns. Z scores are: z = (x - mean)/std, so values in each row (column) will get the mean of the row (column) subtracted, then divided by the standard deviation of the row (column). This ensures that each row (column) has mean of 0 and variance of 1. standard_scale : int or None, optional Either 0 (rows) or 1 (columns). Whether or not to standardize that dimension, meaning for each row or column, subtract the minimum and divide each by its maximum. figsize : tuple of (width, height), optional Overall size of the figure. cbar_kws : dict, optional Keyword arguments to pass to `cbar_kws` in :func:`heatmap`, e.g. to add a label to the colorbar. {row,col}_cluster : bool, optional If ``True``, cluster the {rows, columns}. {row,col}_linkage : :class:`numpy.ndarray`, optional Precomputed linkage matrix for the rows or columns. See :func:`scipy.cluster.hierarchy.linkage` for specific formats. {row,col}_colors : list-like or pandas DataFrame/Series, optional List of colors to label for either the rows or columns. Useful to evaluate whether samples within a group are clustered together. Can use nested lists or DataFrame for multiple color levels of labeling. If given as a :class:`pandas.DataFrame` or :class:`pandas.Series`, labels for the colors are extracted from the DataFrames column names or from the name of the Series. DataFrame/Series colors are also matched to the data by their index, ensuring colors are drawn in the correct order. mask : bool array or DataFrame, optional If passed, data will not be shown in cells where `mask` is True. Cells with missing values are automatically masked. Only used for visualizing, not for calculating. {dendrogram,colors}_ratio : float, or pair of floats, optional Proportion of the figure size devoted to the two marginal elements. If a pair is given, they correspond to (row, col) ratios. cbar_pos : tuple of (left, bottom, width, height), optional Position of the colorbar axes in the figure. Setting to ``None`` will disable the colorbar. tree_kws : dict, optional Parameters for the :class:`matplotlib.collections.LineCollection` that is used to plot the lines of the dendrogram tree. kwargs : other keyword arguments All other keyword arguments are passed to :func:`heatmap`. Returns ------- :class:`ClusterGrid` A :class:`ClusterGrid` instance. See Also -------- heatmap : Plot rectangular data as a color-encoded matrix. Notes ----- The returned object has a ``savefig`` method that should be used if you want to save the figure object without clipping the dendrograms. To access the reordered row indices, use: ``clustergrid.dendrogram_row.reordered_ind`` Column indices, use: ``clustergrid.dendrogram_col.reordered_ind`` Examples -------- .. include:: ../docstrings/clustermap.rst z)clustermap requires scipy to be available) r*r rrr+r,r7r-r.r')rrrgrQrRrSrTr)r r r r)r6r*rrr+r,r rSrQrRrSrTrrr7r-r.r'rrrrrrrzs g ))rr matplotlibr(matplotlib.collectionsrmatplotlib.pyplotpyplotrrnumpyr.pandasrZ scipy.clusterrr rr<raxisgridr_compatrutilsr r r r r __all__rr#r+r9r:rrrr rrrrrs`           %  l6 6G