Python seaborn.jointplot() Examples

def astro_oligo_joint(X, genes, gene1, gene2, labels, focus, name):
    X = X.toarray()

    gidx1 = list(genes).index(gene1)
    gidx2 = list(genes).index(gene2)

    idx = labels == focus

    x1 = X[(idx, gidx1)]
    x2 = X[(idx, gidx2)]

    plt.figure()
    sns.jointplot(
        x1, x2, kind='scatter', space=0, alpha=0.3
    ).plot_joint(sns.kdeplot, zorder=0, n_levels=10)
    plt.savefig('{}_joint_{}_{}_{}.png'.format(name, focus, gene1, gene2)) 

def astro_oligo_joint(X, genes, gene1, gene2, labels, focus, name):
    X = X.toarray()

    gidx1 = list(genes).index(gene1)
    gidx2 = list(genes).index(gene2)

    idx = labels == focus

    x1 = X[(idx, gidx1)]
    x2 = X[(idx, gidx2)]

    plt.figure()
    sns.jointplot(
        x1, x2, kind='scatter', space=0, alpha=0.3
    ).plot_joint(sns.kdeplot, zorder=0, n_levels=10)
    plt.savefig('{}_joint_{}_{}_{}.png'.format(name, focus, gene1, gene2)) 

def jointplot(self, other, column, **kwargs):
        """
        Generate a seaborn jointplot for given column in asset compared to
        another asset.

        Parameters:
            - other: The other asset's dataframe
            - column: The column name to use for the comparison.
            - kwargs: Keyword arguments to pass down to `sns.pairplot()`

        Returns:
            A seaborn jointplot
        """
        return sns.jointplot(
            x=self.data[column],
            y=other[column],
            **kwargs
        ) 

def produce_the_kde_plot(cycles, color, save_name):
    ground_truth_and_suggested = [(eval_code.get_best_qed_from_smiles_bag(elem['ground_truth_product']),
                                   eval_code.get_best_qed_from_smiles_bag(elem['suggested_product']))
                                         for elem in cycles]
    len_out = len(ground_truth_and_suggested)
    ground_truth_and_suggested = [elem for elem in ground_truth_and_suggested if elem[1] != -np.inf]
    len_filter = len(ground_truth_and_suggested)
    num_discarding = len_out - len_filter
    if num_discarding:
        warnings.warn(f"Discarding {num_discarding} our of {len_out} as no successful reconstruction")
    ground_truth_and_suggested = np.array(ground_truth_and_suggested)
    ground_truth_product_qed = ground_truth_and_suggested[:, 0]
    suggested_product_qed = ground_truth_and_suggested[:, 1]

    g = sns.jointplot(x=ground_truth_product_qed, y=suggested_product_qed, kind="kde", color=color,
                      )
    g.set_axis_labels("product's QED", "reconstructed product's QED", fontsize=16)
    rsquare = lambda a, b: stats.pearsonr(ground_truth_product_qed, suggested_product_qed)[0] ** 2
    g = g.annotate(rsquare, template="{stat}: {val:.2f}",
                   stat="$R^2$", loc="upper left", fontsize=12)
    print(f"Rsquare: {stats.pearsonr(ground_truth_product_qed, suggested_product_qed)[0] ** 2}")
    print(f"scipystats: {stats.linregress(ground_truth_product_qed, suggested_product_qed)}")
    plt.tight_layout()
    plt.savefig(f"{save_name}.pdf") 

def visualize_distribution(X,prediction,score,path=None):
    """
    Visualize the original density distribution of the data in 2-dimension space.

    Parameters
    ----------
    X: numpy array of shape (n_test, n_features)
        Test data.
    prediction: numpy array of shape (n_test, )
        The prediction result of the test data.
    score: numpy array of shape (n_test, )
        The outlier score of the test data.
    path: string
        The saving path for result figures.
    """

    sns.set(style="ticks")
    X=X.to_numpy()
    X_embedding = TSNE(n_components=2).fit_transform(X)
    sns_plot=sns.jointplot(X_embedding[:,1],X_embedding[:,0], kind="kde", space=0, color="#4CB391")
    if path:
        sns_plot.savefig(path+'/distribution.png')
    plt.show() 

def gauss_2d(nsamples=1000):
    """
    Another simple test plot
    1d gaussian sampled from each sampler visualized as a joint 2d gaussian
    """
    gaussian = TestGaussian(ndims=1)
    control = HMCBase(distribution=gaussian)
    experimental = MarkovJumpHMC(distribution=gaussian, resample=False)


    with sns.axes_style("white"):
        sns.jointplot(
            control.sample(nsamples)[0],
            experimental.sample(nsamples)[0],
            kind='hex',
            stat_func=None) 

def plot_pop_resids(msm, **kwargs):
    """
    Plot residuals between MSM populations and raw counts.

    Parameters
    ----------
    msm : msmbuilder.msm
        MSMBuilder MarkovStateModel
    **kwargs : dict, optional
        Extra arguments to pass to seaborn.jointplot

    Returns
    -------
    ax : matplotlib axis
        matplotlib figure axis

    """
    if hasattr(msm, 'all_populations_'):
        msm_pop = msm.populations_.mean(0)
    elif hasattr(msm, 'populations_'):
        msm_pop = msm.populations_

    raw_pop = msm.countsmat_.sum(1) / msm.countsmat_.sum()
    ax = sns.jointplot(np.log10(raw_pop), np.log10(msm_pop), kind='resid',
                       **kwargs)
    ax.ax_joint.set_xlabel('Raw Populations', size=20)
    ax.ax_joint.set_ylabel('Residuals', size=20)

    return ax 

def sample_54_1():
    """
    5.4 使用seaborn可视化数据
    :return:
    """
    sns.distplot(tsla_df['p_change'], bins=80)
    plt.show()

    sns.boxplot(x='date_week', y='p_change', data=tsla_df)
    plt.show()

    sns.jointplot(tsla_df['high'], tsla_df['low'])
    plt.show() 

def hist_2d(distr, nsamples, **kwargs):
    """
    Plots a 2d hexbinned histogram of distribution

    Args:
     distr: Distribution object
     nsamples: number of samples to use to generate plot
    """
    sampler = MarkovJumpHMC(distribution=distr, **kwargs)
    samples = sampler.sample(nsamples)

    with sns.axes_style("white"):
       g =  sns.jointplot(samples[0], samples[1], kind='kde', stat_func=None)
    return g 

def plot_euler(theta,phi,psi,plot_psi=True):
    sns.jointplot(theta,phi,kind='hex',
              xlim=(-180,180),
              ylim=(0,180)).set_axis_labels("theta", "phi")
    if plot_psi:
        plt.figure()
        plt.hist(psi)
        plt.xlabel('psi') 

def saveMovg(df,step=12):
    moving_avg = pd.rolling_mean(df['dsc_log'], step)
    sns.jointplot(x=df['time'],y=moving_avg,color='red')
    plt.title('Moving Average')
    plt.savefig(ma_path)

# 创建word文档 

def eval1():
  n_observations = 2000  # number of data points
  n_features = 1  # number of features

  X_train, X_test, y_train, y_test = build_econ1_dataset(n_observations)
  print("Size of features in training data: {}".format(X_train.shape))
  print("Size of output in training data: {}".format(y_train.shape))
  print("Size of features in test data: {}".format(X_test.shape))
  print("Size of output in test data: {}".format(y_test.shape))

  fig, ax = plt.subplots()
  fig.set_size_inches(10, 8)
  sns.regplot(X_train, y_train, fit_reg=False)
  # plt.savefig('toydata.png')
  # plt.show()
  # plot.figure.size = 100
  # plt.show()

  kmn = KernelMixtureNetwork(train_scales=True, n_centers=20)
  kmn.fit(X_train, y_train, n_epoch=300, eval_set=(X_test, y_test))
  kmn.plot_loss()
  # plt.savefig('trainplot.png')
  samples = kmn.sample(X_test)
  print(X_test.shape, samples.shape)
  jp = sns.jointplot(X_test.ravel(), samples, kind="hex", stat_func=None, size=10)
  jp.ax_joint.add_line(Line2D([X_test[0][0], X_test[0][0]], [-40, 40], linewidth=3))
  jp.ax_joint.add_line(Line2D([X_test[1][0], X_test[1][0]], [-40, 40], color='g', linewidth=3))
  jp.ax_joint.add_line(Line2D([X_test[2][0], X_test[2][0]], [-40, 40], color='r', linewidth=3))
  plt.savefig('hexplot.png')
  plt.show()
  d = kmn.predict_density(X_test[0:3, :].reshape(-1, 1), resolution=1000)
  df = pd.DataFrame(d).transpose()
  df.index = np.linspace(kmn.y_min, kmn.y_max, num=1000)
  df.plot(legend=False, linewidth=3, figsize=(12.2, 8))
  plt.savefig('conditional_density.png') 

def plot_correlation(x, y, data, title=None, color=None, kind='joint', ax=None):
    # Extract only pKa values.
    data = data[[x, y]]

    # Find extreme values to make axes equal.
    min_limit = np.ceil(min(data.min()) - 2)
    max_limit = np.floor(max(data.max()) + 2)
    axes_limits = np.array([min_limit, max_limit])

    if kind == 'joint':
        grid = sns.jointplot(x=x, y=y, data=data,
                             kind='reg', joint_kws={'ci': None}, stat_func=None,
                             xlim=axes_limits, ylim=axes_limits, color=color)
        ax = grid.ax_joint
        grid.fig.subplots_adjust(top=0.95)
        grid.fig.suptitle(title)
    elif kind == 'reg':
        ax = sns.regplot(x=x, y=y, data=data, color=color, ax=ax)
        ax.set_title(title)

    # Add diagonal line.
    ax.plot(axes_limits, axes_limits, ls='--', c='black', alpha=0.8, lw=0.7)

    # Add shaded area for 0.5-1 pKa error.
    palette = sns.color_palette('BuGn_r')
    ax.fill_between(axes_limits, axes_limits - 0.5, axes_limits + 0.5, alpha=0.2, color=palette[2])
    ax.fill_between(axes_limits, axes_limits - 1, axes_limits + 1, alpha=0.2, color=palette[3]) 

def plot_correlation(x, y, data, title=None, color=None, kind='joint', ax=None):
    # Extract only pKa values.
    data = data[[x, y]]

    # Find extreme values to make axes equal.
    min_limit = np.ceil(min(data.min()) - 2)
    max_limit = np.floor(max(data.max()) + 2)
    axes_limits = np.array([min_limit, max_limit])

    if kind == 'joint':
        grid = sns.jointplot(x=x, y=y, data=data,
                             kind='reg', joint_kws={'ci': None}, stat_func=None,
                             xlim=axes_limits, ylim=axes_limits, color=color)
        ax = grid.ax_joint
        grid.fig.subplots_adjust(top=0.95)
        grid.fig.suptitle(title)
    elif kind == 'reg':
        ax = sns.regplot(x=x, y=y, data=data, color=color, ax=ax)
        ax.set_title(title)

    # Add diagonal line.
    ax.plot(axes_limits, axes_limits, ls='--', c='black', alpha=0.8, lw=0.7)

    # Add shaded area for 0.5-1 pKa error.
    palette = sns.color_palette('BuGn_r')
    ax.fill_between(axes_limits, axes_limits - 0.5, axes_limits + 0.5, alpha=0.2, color=palette[2])
    ax.fill_between(axes_limits, axes_limits - 1, axes_limits + 1, alpha=0.2, color=palette[3]) 

def plot_correlation(x, y, data, title=None, color=None, kind='joint', ax=None):
    # Extract only logP values.
    data = data[[x, y]]

    # Find extreme values to make axes equal.
    min_limit = np.ceil(min(data.min()) - 1)
    max_limit = np.floor(max(data.max()) + 1)
    axes_limits = np.array([min_limit, max_limit])

    if kind == 'joint':
        grid = sns.jointplot(x=x, y=y, data=data,
                             kind='reg', joint_kws={'ci': None}, stat_func=None,
                             xlim=axes_limits, ylim=axes_limits, color=color)
        ax = grid.ax_joint
        grid.fig.subplots_adjust(top=0.95)
        grid.fig.suptitle(title)
    elif kind == 'reg':
        ax = sns.regplot(x=x, y=y, data=data, color=color, ax=ax)
        ax.set_title(title)

    # Add diagonal line.
    ax.plot(axes_limits, axes_limits, ls='--', c='black', alpha=0.8, lw=0.7)

    # Add shaded area for 0.5-1 logP error.
    palette = sns.color_palette('BuGn_r')
    ax.fill_between(axes_limits, axes_limits - 0.5, axes_limits + 0.5, alpha=0.2, color=palette[2])
    ax.fill_between(axes_limits, axes_limits - 1, axes_limits + 1, alpha=0.2, color=palette[3]) 

def plot_correlation(x, y, data, title=None, color=None, kind='joint', ax=None):
    # Extract only logP values.
    data = data[[x, y]]

    # Find extreme values to make axes equal.
    min_limit = np.ceil(min(data.min()) - 1)
    max_limit = np.floor(max(data.max()) + 1)
    axes_limits = np.array([min_limit, max_limit])

    if kind == 'joint':
        grid = sns.jointplot(x=x, y=y, data=data,
                             kind='reg', joint_kws={'ci': None}, stat_func=None,
                             xlim=axes_limits, ylim=axes_limits, color=color)
        ax = grid.ax_joint
        grid.fig.subplots_adjust(top=0.95)
        grid.fig.suptitle(title)
    elif kind == 'reg':
        ax = sns.regplot(x=x, y=y, data=data, color=color, ax=ax)
        ax.set_title(title)

    # Add diagonal line.
    ax.plot(axes_limits, axes_limits, ls='--', c='black', alpha=0.8, lw=0.7)

    # Add shaded area for 0.5-1 logP error.
    palette = sns.color_palette('BuGn_r')
    ax.fill_between(axes_limits, axes_limits - 0.5, axes_limits + 0.5, alpha=0.2, color=palette[2])
    ax.fill_between(axes_limits, axes_limits - 1, axes_limits + 1, alpha=0.2, color=palette[3]) 

def plot_trajectories(rewards, health, figure_file_obj):
  plt.figure()
  g = sns.jointplot(x=rewards, y=health, kind='kde')
  g.plot_joint(plt.scatter, c='grey', s=30, linewidth=1, marker='+')
  g.ax_joint.collections[0].set_alpha(0)
  g.set_axis_labels('$Reward$', '$Health$')
  if figure_file_obj:
    plt.savefig(figure_file_obj, format='png')
  else:
    plt.show() 

def plot_correlation(x, y, data, title=None, color=None, shaded_area_color=None, hue=None, ax=None):
    import seaborn as sns
    from matplotlib import pyplot as plt

    # Extract only free energies.
    values = data[[x, y]]

    # Find extreme values to make axes equal.
    # Generally plot between -20 and 0, and then
    # set it to the next number divisible by 5.
    min_limit = min(-20, np.floor(min(values.min())/5) * 5)
    max_limit = max(0, np.ceil(max(values.max())/5) * 5)
    axes_limits = np.array([min_limit, max_limit])

    if hue is None:
        grid = sns.jointplot(x=x, y=y, data=data,
                             kind='reg', joint_kws={'ci': None}, stat_func=None,
                             xlim=axes_limits, ylim=axes_limits, color=color)
        ax = grid.ax_joint
        grid.fig.subplots_adjust(top=0.95)
        grid.fig.suptitle(title)
    else:
        unique_hues = sorted(data[hue].unique())
        if ax is None:
            fig, ax = plt.subplots()
        # Set axes limits and ratio.
        ax.set_xlim(axes_limits)
        ax.set_ylim(axes_limits)
        ax.set_aspect('equal', 'box')
        # If a single color is passed, transform it into a palette.
        if not isinstance(color, list):
            color = [color for _ in range(len(unique_hues)+1)]
        # Add regression line single hue and all.
        for value, c in zip(unique_hues, color):
            sns.regplot(x=x, y=y, data=data[data[hue] == value], ci=0, label=value,
                        scatter=True, color=c, line_kws={'alpha': 0.5}, ax=ax)
        # Plot regression line for all the hues together.
        sns.regplot(x=x, y=y, data=data, ci=0, label='All',
                    scatter=False, color=color[len(unique_hues)],
                    line_kws={'alpha': 0.7}, ax=ax)
        ax.legend(loc='upper left')
        ax.set_title(title)

    # Add diagonal line.
    ax.plot(axes_limits, axes_limits, ls='--', c='black', alpha=0.8, lw=0.8)

    # Add shaded area for 1.5 kcal/mol error.
    if shaded_area_color is None:
        shaded_area_color = sns.color_palette('BuGn_r')[2]
    ax.fill_between(axes_limits, axes_limits - 1.5, axes_limits + 1.5, alpha=0.3,
                    color=shaded_area_color)


# =============================================================================
# MAIN SAMPL SUBMISSION CLASS
# ============================================================================= 

def main(args):
    np.random.seed(args.seed)
    f = args.input
    print(f)
    x = pickle.load(open(f,'rb'))
    if args.stride:
        x = x[::args.stride]
    print(x.shape)

    # seaborn jointpoint
    if args.kde:
        g = sns.jointplot(x[:,0],x[:,1], kind='kde')
        ax = g.ax_joint 

    # scatter plot
    else:
        fig,ax = plt.subplots()
        if args.color:
            plt.scatter(x[:,0], x[:,1], c=np.arange(len(x[:,0])), label=f, alpha=args.alpha, s=args.ms, cmap='hsv')
        else:
            plt.scatter(x[:,0], x[:,1], label=f, alpha=args.alpha, s=args.ms)
        plt.xlabel('z1')
        plt.ylabel('z2')
        plt.legend(loc='best')

    if args.sample1:
        ii = np.random.choice(len(x), args.sample1)
        print(ii)
        xd = x[ii]
        print(xd)
        plt.scatter(xd[:,0],xd[:,1],c=np.arange(len(xd)),cmap='hsv')
        if args.annotate:
            for i in range(args.sample1):
                ax.annotate(str(i), xd[i])
    if args.sample2:
        xsplit = np.array_split(x,args.sample2)
        xd = np.array([np.median(xs,axis=0) for xs in xsplit])
        print(len(xd))
        print(xd)
        plt.scatter(xd[:,0],xd[:,1],c='k')#np.arange(len(xd)),cmap='hsv')
    if args.out_s:
        np.savetxt(args.out_s, xd)
    if args.out_png: 
        plt.savefig(args.out_png)
    else:
        plt.show() 

def PerfMonPlotter(perf_mon_records, time_window = None):
    """
    For plotting performance monitoring records.
    """
    # Entire records
    pqos_records = perf_mon_records['pqos_records']
    # perf_records = perf_mon_records['perf_records']
    # # Select a time window if provided
    # if time_window is not None:
    #     test_start = pqos_records['timestamp'].min()
    #     time_window = [5, 10]
    #     selection_bounds = [test_start + timedelta(seconds=time_window[0]), \
    #                         test_start + timedelta(seconds=time_window[1])]
    #     pqos_records['In Test Bound'] = (pqos_records['timestamp']>selection_bounds[0]) \
    #                                     & (pqos_records['timestamp']<selection_bounds[1])
    #     perf_records['In Test Bound'] = (perf_records['timestamp']>time_window[0]) \
    #                                     & (perf_records['timestamp']<time_window[1])
    #     pqos_df = pqos_records[pqos_records['In Test Bound']==True]
    #     perf_df = perf_records[perf_records['In Test Bound']==True]

    palette = sns.color_palette("rocket_r", 16)
    
    # 'timestamp','Core','IPC','LLC Misses','LLC Util (KB)','MBL (MB/s)'
    fig, axs = plt.subplots(ncols=2, nrows=2, sharex=True)
    pqos_records_sum = pqos_records.groupby('timestamp').sum()
    pqos_records_sum.plot(y='IPC', ax=axs[0][0])
    pqos_records_sum.plot(y='MBL (MB/s)', ax=axs[0][1])
    pqos_records_sum.plot(y='LLC Util (KB)', ax=axs[1][0])
    pqos_records_sum.plot(y='LLC Misses', ax=axs[1][1])
    axs[0][0].set_ylim([0,20])

    # sns.relplot(data=pqos_records, x='timestamp', y='IPC', hue='Core', kind='line', palette=palette, alpha=0.75)
    # sns.relplot(data=pqos_records, x='timestamp', y='MBL (MB/s)', hue='Core', kind='scatter', palette=palette, alpha=0.75)
    # sns.lmplot(data=pqos_df.groupby('timestamp').sum(), x='IPC', y='MBL (MB/s)', palette=palette,
    #            truncate=True, order=5, fit_reg=False, scatter_kws={'alpha':0.5}, legend_out=False)
    # sns.jointplot(data=pqos_df.groupby('timestamp').sum(), x='LLC Util (KB)', y='MBL (MB/s)', kind="hex", zorder=0)
                #  .plot_joint(sns.kdeplot, zorder=10, n_levels=25, bw='silverman')

    # cpu-cycles,L1-dcache-loads,L1-dcache-load-misses,L1-icache-load-misses,dTLB-load-misses,dTLB-loads,
    # iTLB-load-misses,iTLB-loads,branch-misses,context-switches,cpu-migrations,page-faults
    # sns.relplot(data=perf_records, x='timestamp', y='context-switches', kind='line', palette=palette, alpha=0.75)
    # plt.stackplot(perf_records['timestamp'], perf_records['r4f1'], perf_records['r2f1'], perf_records['r1f1'])
    # sns.relplot(data=perf_df, x='context-switches', y='r1f1', kind='scatter', palette=palette, alpha=0.75)
    # perf_records['Branch Miss Rate (%)'] = 100.0*perf_records['branch-misses']/perf_records['branches']
    # sns.lmplot(data=perf_records, x='context-switches', y='block:block_plug',
    #            truncate=True, order=8, scatter_kws={'alpha':0.5}, legend_out=False)
    # sns.jointplot(data=perf_df, x='dTLB-loads', y='iTLB-loads', kind="hex", zorder=0)

    plt.show()
    plt.close()

    return True 

def visualisationDF(df):    
    dataFrameInfoPrint(df)
    #graph-01
    # df['shapelyArea'].plot.hist(alpha=0.5)    
    #graph-02
    # df['shapelyArea'].plot.kde()    
    #graph-03
    # df[['shapelyLength','shapeIdx']].plot.scatter('shapelyLength','shapeIdx')    
    #normalize data in a range of columns
    cols_to_norm=['shapeIdx', 'FRAC']
    df[cols_to_norm]=df[cols_to_norm].apply(lambda x: (x - x.min()) / (x.max() - x.min()))
    
    a='shapeIdx'
    b='FRAC'
    c='park_class'
    
    #graph-04
    # sns.jointplot(a,b,df,kind='hex')
    
    #graph-05
    # sns.jointplot(a, b, df, kind='kde')
    
    #graph-06
    # sns.catplot(x='park_class',y=a,data=df)
    
    #graph-07
    '''
    # Initialize the figure
    f, ax = plt.subplots()
    sns.despine(bottom=True, left=True)
    # Show each observation with a scatterplot
    sns.stripplot(x=a, y=c, hue=c,data=df, dodge=True, alpha=.25, zorder=1)    
    # Show the conditional means
    sns.pointplot(x=a, y=c, hue=c,data=df, dodge=.532, join=False, palette="dark",markers="d", scale=.75, ci=None)
    # Improve the legend 
    handles, labels = ax.get_legend_handles_labels()
    ax.legend(handles[3:], labels[3:], title=b,handletextpad=0, columnspacing=1,loc="lower right", ncol=3, frameon=True)
    '''
    
    #graph-08
    # sns.catplot(x=c,y=a,data=df,kind='box')
    
    #graph-09
    # sns.catplot(x=c,y=a,data=df,kind='violin')
    
    #graph-10
    '''
    f, axs = plt.subplots(1, 2, figsize=(12, 6))
    # First axis    
    df[b].plot.hist(ax=axs[0])
    # Second axis
    df[b].plot.kde(ax=axs[1])
    # Title
    f.suptitle(b)
    # Display
    plt.show()
    '''        

#从新定义栅格投影，参考投影为vector .shp文件 

def run(self, params={}):
        # Set styles
        sns.set_palette(params.get('color_palette'))
        sns.set(style=params.get('margin_style'))

        # Process the data and create the plot
        try:
            decoded_data = base64.b64decode(params.get('csv_data'))
        except Exception as e:
            error = f"Failed to decode base64 encoded CSV data with error: {e}"
            self.logger.error(error)
            raise e

        df = pd.read_csv(BytesIO(decoded_data))
        x = params.get('x_value')
        y = params.get('y_value')
        kind = params.get('kind')

        args = {
            "data": df,
            "x": x,
            "y": y,
            "kind": kind
        }

        if not x or (x not in df):
            error = f"Column for X value({x}) not in data set, cannot create plot..."
            self.logger.error(error)
            return Exception(error)
        elif not y or (y not in df):
            error = f"Column for Y value ({y}) not in data set, cannot create plot..."
            self.logger.error(error)
            return Exception(error)

        # JointPlots have the savefig method, call it directly
        self.logger.info("Creating plot...")
        plot = sns.jointplot(**args)

        # bbox_inches is required to ensure that labels are cut off
        plot.savefig('plot.png', bbox_inches='tight')
        with open('plot.png', 'rb', )as f:
            plot = base64.b64encode(f.read())

        return {
            "csv": params.get('csv_data'),
            "plot": plot.decode('utf-8')
        }