Python seaborn.violinplot方法代碼示例

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def quality_over_time(dfs, path, figformat, title, plot_settings={}):
    time_qual = Plot(path=path + "TimeQualityViolinPlot." + figformat,
                     title="Violin plot of quality over time")
    sns.set(style="white", **plot_settings)
    ax = sns.violinplot(x="timebin",
                        y="quals",
                        data=dfs,
                        inner=None,
                        cut=0,
                        linewidth=0)
    ax.set(xlabel='Interval (hours)',
           ylabel="Basecall quality",
           title=title or time_qual.title)
    plt.xticks(rotation=45, ha='center', fontsize=8)
    time_qual.fig = ax.get_figure()
    time_qual.save(format=figformat)
    plt.close("all")
    return time_qual 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def sequencing_speed_over_time(dfs, path, figformat, title, plot_settings={}):
    time_duration = Plot(path=path + "TimeSequencingSpeed_ViolinPlot." + figformat,
                         title="Violin plot of sequencing speed over time")
    sns.set(style="white", **plot_settings)
    if "timebin" not in dfs:
        dfs['timebin'] = add_time_bins(dfs)
    mask = dfs['duration'] != 0
    ax = sns.violinplot(x=dfs.loc[mask, "timebin"],
                        y=dfs.loc[mask, "lengths"] / dfs.loc[mask, "duration"],
                        inner=None,
                        cut=0,
                        linewidth=0)
    ax.set(xlabel='Interval (hours)',
           ylabel="Sequencing speed (nucleotides/second)",
           title=title or time_duration.title)
    plt.xticks(rotation=45, ha='center', fontsize=8)
    time_duration.fig = ax.get_figure()
    time_duration.save(format=figformat)
    plt.close("all")
    return time_duration 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def violin_jitter(X, genes, gene, labels, focus, background=None,
                  xlabels=None):
    gidx = list(genes).index(gene)

    focus_idx = focus == labels
    if background is None:
        background_idx = focus != labels
    else:
        background_idx = background == labels

    if xlabels is None:
        xlabels = [ 'Background', 'Focus' ]

    x_gene = X[:, gidx].toarray().flatten()
    x_focus = x_gene[focus_idx]
    x_background = x_gene[background_idx]
    
    plt.figure()
    sns.violinplot(data=[ x_focus, x_background ], scale='width', cut=0)
    sns.stripplot(data=[ x_focus, x_background ], jitter=True, color='black', size=1)
    plt.xticks([0, 1], xlabels)
    plt.savefig('{}_violin_{}.png'.format(NAMESPACE, gene)) 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def violinplot(set_size, p_error, subplot, i):
    """Make learning cuves with violinplot.

    Parameters
    ----------
    set_size : list
       Size of sub-set of data/features which the model is based on.
    p_error : list
       The prediction error for plain vanilla ridge.
    subplot : int
        Which subplot being produced.
    i : int
       Which iteration in the featureselection.
    """
    plt.figure(1)
    plt.subplot(int("22" + str(subplot))).set_title('Feature size ' + str(i),
                                                    loc='left')
    plt.legend(loc='upper right')
    plt.ylabel('Prediction error')
    plt.xlabel('Data size')
    sns.violinplot(x=set_size, y=p_error, scale="count")
    sns.pointplot(x=set_size, y=p_error, ci=100, capsize=.2)
    if subplot == 4:
        plt.show() 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def featselect_featvar_plot(p_error_select, number_feat):
    """Create learning curve with data size and prediction error.

    Parameters
    ----------
    data_size : list
        Data_size for where the prediction were made.
    p_error : list
        Error for where the prediction were made.
    data_size_mean : list
        Mean of the data size in a sub-set.
    p_error_mean : list
        The mean error for the sub-set.
    corrected_std : array
        The standard deaviation for the sub-set of data.
    """
    fig = plt.figure()
    fig.add_subplot(111)
    sns.violinplot(x=number_feat, y=p_error_select, scale="count")
    sns.pointplot(x=number_feat, y=p_error_select)
    plt.legend(loc='upper right')
    plt.ylabel('Prediction error')
    plt.xlabel('Data size')
    plt.show() 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def metal_distance_widget(df_concat):
    '''Plot an violinplot of metal-element distances with ipywidgets

    Parameters
    ----------
    df_concat : Dataframe
       dataframe of metal-elements distances

    '''
    metals = df_concat['Metal'].unique().tolist()
    m_widget = Dropdown(options = metals, description = "Metals")

    def metal_distance_violinplot(metal):
        df_metal = df_concat[df_concat["Metal"] == metal].copy()
        df_metal['Element'] = df_metal['Element'].apply(lambda x: metal+"-"+x)

        # Set fonts
        fig, ax = plt.subplots()
        fig.set_size_inches(15,6)
        subplot = sns.violinplot(x="Element", y="Distance", palette="muted", data=df_metal, ax=ax)
        subplot.set(xlabel="Metal Interactions", ylabel="Distance", title=f"{metal} to Elements Distances Violin Plot")

    return interact(metal_distance_violinplot, metal=m_widget); 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def bar_box_violin_dot_plots(data, category_col, numeric_col, axes, file_name=None):
    sns.barplot(category_col, numeric_col, data=data, ax=axes[0])
    sns.boxplot(
        category_col, numeric_col, data=data[data[numeric_col].notnull()], ax=axes[2]
    )
    sns.violinplot(
        category_col,
        numeric_col,
        data=data,
        kind="violin",
        inner="quartile",
        scale="count",
        split=True,
        ax=axes[3],
    )
    sns.stripplot(category_col, numeric_col, data=data, jitter=True, ax=axes[1])
    sns.despine(left=True) 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def fig6():
    """ violin plot for the physicochemical proerties comparison.
        A: molecules generated by pre-trained model v.s. ZINC set.
        B: molecules generated by fine-tuned model v.s. A2AR set.
    """
    plt.figure(figsize=(12, 6))
    plt.subplot(121)
    sns.set(style="white", palette="pastel", color_codes=True)
    df = properties(['data/ZINC_B.txt', 'mol_p.txt'], ['ZINC Dataset', 'Pre-trained Model'])
    sns.violinplot(x='Property', y='Number', hue='Set', data=df, linewidth=1, split=True, bw=1)
    sns.despine(left=True)
    plt.ylim([0.0, 18.0])
    plt.xlabel('Structural Properties')

    plt.subplot(122)
    df = properties(['data/CHEMBL251.txt', 'mol_ex.txt'], ['A2AR Dataset', 'Fine-tuned Model'])
    sns.set(style="white", palette="pastel", color_codes=True)
    sns.violinplot(x='Property', y='Number', hue='Set', data=df, linewidth=1, split=True, bw=1)
    sns.despine(left=True)
    plt.ylim([0.0, 18.0])
    plt.xlabel('Structural Properties')
    plt.tight_layout()
    plt.savefig('Figure_6.tif', dpi=300) 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def fig9():
    """ violin plot for the physicochemical proerties comparison.
            1: molecules generated by DrugEx with pre-trained model as exploration network.
            2: molecules generated by DrugEx with fine-tuned model as exploration network.
        """
    fig = plt.figure(figsize=(12, 12))
    ax1 = fig.add_subplot(211)
    sns.set(style="white", palette="pastel", color_codes=True)
    df = properties(mol_paths + real_path, labels + real_label, is_active=True)
    sns.violinplot(x='Property', y='Number', hue='Set', data=df, linewidth=1, bw=0.8)
    sns.despine(left=True)
    ax1.set(ylim=[0.0, 15.0], xlabel='Structural Properties')

    ax2 = fig.add_subplot(212)
    df = properties(mol_paths1 + real_path, labels + real_label, is_active=True)
    sns.set(style="white", palette="pastel", color_codes=True)
    sns.violinplot(x='Property', y='Number', hue='Set', data=df, linewidth=1, bw=0.8)
    sns.despine(left=True)
    ax2.set(ylim=[0.0, 15.0], xlabel='Structural Properties')
    fig.tight_layout()
    fig.savefig('Figure_9.tif', dpi=300) 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def plot_change_by_pos(diffs_by_context,plottype='box'):
    fig = plt.figure(figsize=(6,4))
    changes_by_position = {'position':[],'base':[],'diff':[]}
    for lab in diffs_by_context:
        for context in diffs_by_context[lab]:
            for entry in diffs_by_context[lab][context]:
                for pos,diff in enumerate(entry[:-1]):
                    changes_by_position['position'].append(pos+1)
                    changes_by_position['base'].append(lab)
                    changes_by_position['diff'].append(diff)
    dPos = pd.DataFrame(changes_by_position)
    if plottype == 'box':
        sns.boxplot(x="position", y="diff", hue="base", data=dPos, palette=[cols[base],cols[methbase]])
    elif plottype == 'violin':
        sns.violinplot(x="position",y="diff", hue="base", data=dPos, palette=[cols[base],cols[methbase]])
    sns.despine(trim=False)
    plt.xlabel('Adenine Position in 6-mer')
    plt.ylabel('Measured - Expected Current (pA)')
    plt.ylim([-20,20])
    plt.legend(title='',loc='upper center', bbox_to_anchor=(0.5, 1.05),
          ncol=3, fancybox=True)
    plt.savefig('change_by_position_box.pdf',transparent=True,dpi=500, bbox_inches='tight') 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def length_over_time(dfs, path, figformat, title, log_length=False, plot_settings={}):
    if log_length:
        time_length = Plot(path=path + "TimeLogLengthViolinPlot." + figformat,
                           title="Violin plot of log read lengths over time")
    else:
        time_length = Plot(path=path + "TimeLengthViolinPlot." + figformat,
                           title="Violin plot of read lengths over time")
    sns.set(style="white", **plot_settings)
    if log_length:
        length_column = "log_lengths"
    else:
        length_column = "lengths"

    if "length_filter" in dfs:  # produced by NanoPlot filtering of too long reads
        temp_dfs = dfs[dfs["length_filter"]]
    else:
        temp_dfs = dfs

    ax = sns.violinplot(x="timebin",
                        y=length_column,
                        data=temp_dfs,
                        inner=None,
                        cut=0,
                        linewidth=0)
    ax.set(xlabel='Interval (hours)',
           ylabel="Read length",
           title=title or time_length.title)
    if log_length:
        ticks = [10**i for i in range(10) if not 10**i > 10 * np.amax(dfs["lengths"])]
        ax.set(yticks=np.log10(ticks),
               yticklabels=ticks)
    plt.xticks(rotation=45, ha='center', fontsize=8)
    time_length.fig = ax.get_figure()
    time_length.save(format=figformat)
    plt.close("all")
    return time_length 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def astro_oligo_violin(X, genes, gene, labels, name):
    X = X.toarray()

    gidx = list(genes).index(gene)

    astro = X[labels == 'astro', gidx]
    oligo = X[labels == 'oligo', gidx]
    both = X[labels == 'both', gidx]

    plt.figure()
    sns.violinplot(data=[ astro, oligo, both ], scale='width', cut=0)
    sns.stripplot(data=[ astro, oligo, both ], jitter=True, color='black', size=1)
    plt.xticks([0, 1, 2], ['Astrocytes', 'Oligodendrocytes', 'Both'])
    plt.savefig('{}_violin_{}.svg'.format(name, gene)) 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def horizontal_violin_plot(data, ordered_genomes, title, xlabel, pdf, hue=None, x=None, y=None, xlim=None):
    """not so generic function that specifically produces a paired boxplot/violinplot"""
    fig, ax = plt.subplots()
    sns.violinplot(data=data, x=x, y=y, hue=hue, order=ordered_genomes, palette=choose_palette(ordered_genomes),
                   saturation=boxplot_saturation, orient='h', cut=0, scale='count', ax=ax)
    fig.suptitle(title)
    ax.set_xlabel(xlabel)
    if xlim is not None:
        ax.set_xlim(xlim)
    multipage_close(pdf, tight_layout=False) 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def run_kruskal(df, condition_col, value_col='acc_diff', min_n_obs=6, 
                plot=False):
    """Run Kruskal-Wallis analysis of variance test.

    Args:
        df (pd.DataFrame): dataframe where each row is a paper.
        condition_col (str): name of column to use as condition.

    Keyword Args:
        value_col (str): name of column to use as the numerical value to run the
            test on.
        min_n_obs (int): minimum number of observations in each sample in order
            to run the test.

    Returns:
        (float): U statistic
        (float): p-value
    """
    data = [i for name, i in df.groupby(condition_col)[value_col]
            if len(i) >= min_n_obs]

    if len(data) > 2:
        stat, p = kruskal(*data)
    else:
        stat, p = np.nan, np.nan
        print('Not enough samples with more than {} observations.'.format(min_n_obs))

    if plot:
        enough_samples = df[condition_col].value_counts() >= min_n_obs
        enough_samples = enough_samples.index[enough_samples].tolist()
        fig, ax = plt.subplots()
        sns.violinplot(
            data=df[df[condition_col].isin(enough_samples)], x=condition_col, 
            y=value_col, ax=ax)
        ax.set_title('Kruskal-Wallis for {} vs. {}\n(pvalue={:0.4f})'.format(
            condition_col, value_col, p))
    else:
        fig = None

    return {'test': 'kruskal', 'pvalue': p, 'stat': stat, 'fig': fig} 

# 需要導入模塊: import seaborn [as 別名]
# 或者: from seaborn import violinplot [as 別名]
def generate_molecules_plot(self):
        # Correlation plot by molecules.
        plt.close('all')
        data_ordered_by_mol_ID = self.data.sort_values(["Molecule ID"], ascending=["True"])
        sns.set(rc={'figure.figsize': (8.27,11.7)})
        sns.violinplot(y='Molecule ID', x='$\Delta$logP error (calc - exp)', data=data_ordered_by_mol_ID,
                           inner='point', linewidth=1, width=1.2)
        plt.tight_layout()
        # plt.show()
        plt.savefig(os.path.join(self.output_directory_path, self.LOGP_CORRELATION_PLOT_BY_LOGP_PATH_DIR))