python类factorplot()的实例源码

def plot_count_fig(tasks):
    """
    Create count plot, as a 2-row x 3-col bar plot of data points for each k in each covar.

    Parameters
    ----------
    tasks: list(dict)

    Returns
    -------
    Matplotlib Figure object.
    """
    sns.set(context='talk', style='whitegrid')
    df = pd.DataFrame(filter_dict_list_by_keys(tasks, ['k', 'covar_type', 'covar_tied']))
    df = df.loc[:, ['k', 'covar_type', 'covar_tied', 'bic', 'aic']]
    df['covar_type'] = [x.capitalize() for x in df['covar_type']]
    df['covar_tied'] = [['Untied', 'Tied'][x] for x in df['covar_tied']]
    f = sns.factorplot(x='k', kind='count', col='covar_type', row='covar_tied', data=df,
                      row_order=['Tied', 'Untied'], col_order=['Full', 'Diag', 'Spher'], legend=True, legend_out=True,
                      palette='Blues_d')
    f.set_titles("{col_name}-{row_name}")
    f.set_xlabels("Num. of Clusters (K)")
    return f.fig

def plot_grid_scores(model, x, y=None, hue=None, row=None, col=None, col_wrap=None,
                     **kwargs):
    '''
    Wrapper around seaborn.factorplot.

    Parameters
    ----------
    model : Pipeline or Estimator
    x, hue, row, col : str
        parameters grid searched over
    y : str
        the target of interest, default `'mean_'`

    Returns
    -------
    g : seaborn.FacetGrid
    '''
    scores = unpack_grid_scores(model)
    y = y or 'mean_'
    return sns.factorplot(x=x, y=y, hue=hue, row=row, col=col, data=scores,
                          col_wrap=col_wrap, **kwargs)

def denovo_plot(consensus_data, ordered_genomes, denovo_tgt):
    with denovo_tgt.open('w') as outf, PdfPages(outf) as pdf:
        df = json_biotype_nested_counter_to_df(consensus_data, 'denovo')
        # fix column names because json_biotype_nested_counter_to_df makes assumptions
        df.columns = ['Result', 'Number of transcripts', 'Augustus mode', 'genome']
        has_pb = len(set(df['Augustus mode'])) == 2
        if len(set(df.genome)) > 1:  # if we ran in PB only, we may not have multiple genomes
            if has_pb is True:
                ax = sns.factorplot(data=df, x='genome', y='Number of transcripts', kind='bar', col='Result',
                                    hue='Augustus mode', col_wrap=2, row_order=ordered_genomes, sharex=True,
                                    sharey=False)
            else:
                ax = sns.factorplot(data=df, x='genome', y='Number of transcripts', kind='bar', col='Result',
                                    col_wrap=2, row_order=ordered_genomes, sharex=True, sharey=False)
        else:
            if has_pb is True:
                ax = sns.factorplot(data=df, x='Result', y='Number of transcripts', kind='bar', hue='Augustus mode')
            else:
                ax = sns.factorplot(data=df, x='Result', y='Number of transcripts', kind='bar')
        ax.set_xticklabels(rotation=90)
        ax.fig.suptitle('Incorporation of de-novo predictions')
        ax.fig.subplots_adjust(top=0.9)
        multipage_close(pdf, tight_layout=False)

def _plotWeekdayStats(stats, columns, groupBy=True):
    dataToPlot = stats.copy()
    # Group by weekday and rename date column
    if groupBy:
        dataToPlot = dataToPlot.groupby(stats['date'].dt.weekday).mean()
        dataToPlot = dataToPlot.reset_index().rename(columns={'date':'weekday'})

    # change stats from columns to row attribute
    dataToPlot = pd.melt(dataToPlot, id_vars=['weekday'], value_vars=columns,
                         var_name='stats', value_name='val')
    # Rename stats and weekdays
    dataToPlot['stats'].replace(NAMES, inplace=True)
    dataToPlot['weekday'].replace(dayOfWeek, inplace=True)
    # Plot
    g = sns.factorplot(data=dataToPlot, x="weekday", y="val", col="stats",
                       order=dayOfWeekOrder, kind="point", sharey=False, col_wrap=3)
    g.set_xticklabels(rotation=45)
    g.set(xlabel='')
    return g
    #sns.plt.show()

def plotYearAndMonthStatsSleep(stats, columns=None):
    """
    Plot aggregated (mean) stats by year and month.
    :param stats: data to plot
    """
    if not columns:
        columns = ['sleep_efficiency', 'sleep_hours']

    dataToPlot = _prepareYearAndMonthStats(stats, columns)
    # Plot
    g = sns.factorplot(data=dataToPlot, x="date", y="val", row="stats", kind="point", sharey=False)
    g.set_xticklabels(rotation=45)
    for ax in g.axes.flat:
        ax.grid(b=True)
    return g
    #sns.plt.show()

def plot_aic_bic_fig(tasks):
    """
    Creates AIC-BIC plot, as a 2-row x 3-col grid of point plots with 95% confidence intervals.

    Parameters
    ----------
    tasks: list(dict)

    Returns
    -------
    Matplotlib Figure object
    """
    sns.set(context='talk', style='whitegrid')
    # Filter list of dicts to reduce the size of Pandas DataFrame
    df = pd.DataFrame(filter_dict_list_by_keys(tasks, ['k', 'covar_type', 'covar_tied', 'bic', 'aic']))
    df['covar_type'] = [x.capitalize() for x in df['covar_type']]
    df['covar_tied'] = [['Untied', 'Tied'][x] for x in df['covar_tied']]
    df['aic'] = df['aic'].astype('float')
    df['bic'] = df['bic'].astype('float')
    df = pd.melt(df, id_vars=['k', 'covar_type', 'covar_tied'], value_vars=['aic', 'bic'], var_name='metric')
    f = sns.factorplot(x='k', y='value', col='covar_type', row='covar_tied', hue='metric', data=df,
                       row_order=['Tied', 'Untied'], col_order=['Full', 'Diag', 'Spher'], legend=True, legend_out=True,
                       ci=95, n_boot=100)
    f.set_titles("{col_name}-{row_name}")
    f.set_xlabels("Num. of Clusters (K)")
    return f.fig

def mem_svg(self, table, column, outfile):
        import matplotlib
        matplotlib.use('Agg')
        import matplotlib.pyplot as plt
        import seaborn as sb
        sb.set(style="whitegrid")

        svgdat = (table.
            rename(columns={ column : 'Memory' }).
            groupby(['Dataset', 'Threads', 'Program']).
            agg({ 'Memory' : max }).
            reset_index())
        svgdat = svgdat.assign(MemoryMB=svgdat['Memory'] / 1000000)

        threads = svgdat.Threads.unique()
        if len(threads) == 1:
            plot = sb.factorplot(
                x='Program', y='MemoryMB', col="Dataset", 
                data=svgdat, kind="bar", ci=None, sharey=True)
        else:
            plot = sb.factorplot(
                x='Threads', y='MemoryMB', col="Dataset", hue="Program", 
                data=svgdat, kind="bar", ci=None, sharey=True)

        if len(threads) == 1:
            plot = plot.set_titles('')

        plot = plot.set_xlabels('Threads')
        plot = plot.set_ylabels('Memory (MB)')
        plot = plot.set_xticklabels(rotation=90)
        plot.fig.subplots_adjust(wspace=0.35)
        plot.savefig(outfile)

def consensus_support_plot(consensus_data, ordered_genomes, biotypes, modes, title, tgt):
    """grouped violin plots of original intron / intron annotation / exon annotation support"""
    def adjust_plot(g, this_title):
        g.set_xticklabels(rotation=90)
        g.fig.suptitle(this_title)
        g.fig.subplots_adjust(top=0.9)
        for ax in g.axes.flat:
            ax.set_ylabel('Percent supported')
            ax.set_ylim(-1, 101)

    dfs = []
    for i, mode in enumerate(modes):
        df = json_to_df_with_biotype(consensus_data, mode)
        if i > 0:
            df = df[mode]
        dfs.append(df)
    df = pd.concat(dfs, axis=1)
    df = pd.melt(df, value_vars=modes, id_vars=['genome', 'biotype'])
    with tgt.open('w') as outf, PdfPages(outf) as pdf:
        if len(ordered_genomes) > 1:
            g = sns.factorplot(data=df, y='value', x='genome', col='variable', col_wrap=2, kind='violin', sharex=True,
                               sharey=True, row_order=ordered_genomes, cut=0)
        else:
            g = sns.factorplot(data=df, y='value', x='variable', kind='violin', sharex=True,
                               sharey=True, row_order=ordered_genomes, cut=0)
        adjust_plot(g, title)
        multipage_close(pdf, tight_layout=False)
        title += ' for {}'
        for biotype in biotypes:
            this_title = title.format(biotype)
            biotype_df = biotype_filter(df, biotype)
            if biotype_df is not None:
                if len(ordered_genomes) > 1:
                    g = sns.factorplot(data=biotype_df, y='value', x='genome', col='variable', col_wrap=2,
                                       kind='violin', sharex=True, sharey=True, row_order=ordered_genomes, cut=0)
                else:
                    g = sns.factorplot(data=df, y='value', x='variable', kind='violin', sharex=True,
                                       sharey=True, row_order=ordered_genomes, cut=0)
                adjust_plot(g, this_title)
                multipage_close(pdf, tight_layout=False)

def tm_gene_family_plot(tm_data, ordered_genomes, biotypes, gene_family_tgt):
    """transMap gene family collapse plots."""
    try:
        df = json_biotype_nested_counter_to_df(tm_data, 'Gene Family Collapse')
    except ValueError:  # no gene family collapse. probably the test set.
        with gene_family_tgt.open('w') as outf:
            pass
        return
    df['Gene Family Collapse'] = pd.to_numeric(df['Gene Family Collapse'])
    tot_df = df[['Gene Family Collapse', 'genome', 'count']].\
        groupby(['genome', 'Gene Family Collapse']).aggregate(sum).reset_index()
    tot_df = tot_df.sort_values('Gene Family Collapse')
    with gene_family_tgt.open('w') as outf, PdfPages(outf) as pdf:
        g = sns.factorplot(y='count', col='genome', x='Gene Family Collapse', data=tot_df, kind='bar',
                           col_order=ordered_genomes, col_wrap=4)
        g.fig.suptitle('Number of genes collapsed during gene family collapse')
        g.set_xlabels('Number of genes collapsed to one locus')
        g.set_ylabels('Number of genes')
        multipage_close(pdf)
        for biotype in biotypes:
            biotype_df = biotype_filter(df, biotype)
            if biotype_df is None:
                continue
            biotype_df = biotype_df.sort_values('Gene Family Collapse')
            g = sns.factorplot(y='count', col='genome', x='Gene Family Collapse', data=biotype_df, kind='bar',
                               col_order=ordered_genomes, col_wrap=4)
            g.fig.suptitle('Number of genes collapsed during gene family collapse for {}'.format(biotype))
            g.set_xlabels('Number of genes collapsed to one locus')
            g.set_ylabels('Number of genes')
            multipage_close(pdf)

def pb_support_plot(consensus_data, ordered_genomes, pb_genomes, pb_support_tgt):
    with pb_support_tgt.open('w') as outf, PdfPages(outf) as pdf:
        pb_genomes = [x for x in ordered_genomes if x in pb_genomes]  # fix order
        df = json_biotype_counter_to_df(consensus_data, 'IsoSeq Transcript Validation')
        df.columns = ['IsoSeq Transcript Validation', 'Number of transcripts', 'genome']
        ax = sns.factorplot(data=df, x='genome', y='Number of transcripts', hue='IsoSeq Transcript Validation',
                            kind='bar', row_order=pb_genomes)
        ax.set_xticklabels(rotation=90)
        ax.fig.suptitle('Isoforms validated by at least one IsoSeq read')
        multipage_close(pdf, tight_layout=False)

def indel_plot(consensus_data, ordered_genomes, indel_plot_tgt):
    with indel_plot_tgt.open('w') as outf, PdfPages(outf) as pdf:
        tm_df = pd.concat([pd.DataFrame.from_dict(consensus_data[genome]['transMap Indels'], orient='index').T
                           for genome in ordered_genomes])
        tm_df['genome'] = ordered_genomes
        tm_df['transcript set'] = ['transMap'] * len(tm_df)
        consensus_df = pd.concat([pd.DataFrame.from_dict(consensus_data[genome]['Consensus Indels'], orient='index').T
                                  for genome in ordered_genomes])
        consensus_df['genome'] = ordered_genomes
        consensus_df['transcript set'] = ['Consensus'] * len(consensus_df)
        df = pd.concat([consensus_df, tm_df])
        df = pd.melt(df, id_vars=['genome', 'transcript set'],
                     value_vars=['CodingDeletion', 'CodingInsertion', 'CodingMult3Indel'])
        df.columns = ['Genome', 'Transcript set', 'Type', 'Percent of transcripts']
        g = sns.factorplot(data=df, x='Genome', y='Percent of transcripts', col='Transcript set',
                           hue='Type', kind='bar', row_order=ordered_genomes,
                           col_order=['transMap', 'Consensus'])
        g.set_xticklabels(rotation=90)
        g.fig.subplots_adjust(top=.8)
        g.fig.suptitle('Coding indels')
        multipage_close(pdf, tight_layout=False)


###
# shared plotting functions
###

def plot_models(accs):
    cv_df = pd.DataFrame(accs, columns=['model','pipeline', 'score'])
    sns.factorplot(x='model',y='score', hue='pipeline', data=cv_df, kind='bar')

def two_way_factor_plot(dataFrame, x, y, col, row):
    sns.factorplot(x=x, y=y, col=col, row=row,
        data=dataFrame, kind='bar', margin_titles=True, size=3, aspect=.8,
        palette="Set3")

def factorplots(wine_set):
    seaborn.factorplot(x="quality", y="alcohol", data=wine_set, kind="strip")
    plt.xlabel("Quality level of wine, 0-10 scale")
    plt.ylabel("Alcohol level in wine, % ABV")
    if wine_set.equals(red):
        plt.title("Alcohol percent in each level of red wine's quality")
    else:
        plt.title("Alcohol percent in each level of white wine's quality")
    plt.show()

def _plotMonthlyStats(stats, columns, groupBy=True):
    dataToPlot = stats.copy()
    # Group by month and rename date column
    if groupBy:
        dataToPlot = dataToPlot.groupby(stats['date'].dt.month).mean()
        dataToPlot = dataToPlot.reset_index().rename(columns={'date': 'month'})

    # change stats from columns to row attribute
    dataToPlot = pd.melt(dataToPlot, id_vars=['month'], value_vars=columns,
                         var_name='stats', value_name='val')
    # Rename stats and weekdays
    dataToPlot['stats'].replace(NAMES, inplace=True)
    dataToPlot['month'].replace(months, inplace=True)
    order = [m for m in monthsOrder if m in dataToPlot['month'].unique()]
    # Plot
    g = sns.factorplot(data=dataToPlot, x="month", y="val", col="stats", order=order, kind="bar", sharey=False)
    g.set_xticklabels(rotation=45)
    g.set(xlabel='')
    return g
    #sns.plt.show()

# def _plotMonthlyStats(stats, columns):
#     """
#     Plot aggregated (mean) stats by month
#     :param stats: data to plot
#     :param columns: columns from stats to plot
#     """
#     MEASURE_NAME = 'month'
#     months={1:'Jan', 2:'Feb', 3:'Mar', 4:'Apr', 5:'May', 6:'Jun', 7:'Jul', 8:'Aug',
#             9:'Sep', 10:'Oct', 11:'Nov', 12:'Dec'}
#     order = ['Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec']
#     stats[MEASURE_NAME] = stats[MEASURE_NAME].map(months)
#
#     order = [m for m in order if m in stats[MEASURE_NAME].unique()]
#
#     f, axes = getAxes(2,2)
#     for i, c in enumerate(columns):
#         if c in NAMES:
#             c = NAMES[c]
#         g = sns.barplot(x=MEASURE_NAME, y=c, data=stats, order=order, ax=axes[i])
#         g.set_xlabel('')
#     sns.plt.show()