How to use the seaborn.kdeplot function in seaborn

To help you get started, we’ve selected a few seaborn examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github algorithmica-repository / datascience / 2018-jan / 9.supervised ML algorithms / objective based learning / View on Github external
if(size == 1): 
        return 'Single'
    elif(size <=3): 
        return 'Small'
    elif(size <= 6): 
        return 'Medium'
        return 'Large'
titanic_all['FamilyCategory'] = titanic_all['FamilySize'].map(convert_family_size)

def extract_title(name):
     return name.split(',')[1].split('.')[0].strip()
titanic_all['Title'] = titanic_all['Name'].map(extract_title)

tmp_df = titanic_all[0:titanic_train.shape[0]]
sns.FacetGrid(tmp_df, row="Survived",size=8).map(sns.kdeplot, "FamilySize").add_legend()
sns.factorplot(x="Title", hue="Survived", data=tmp_df, kind="count", size=6)
sns.factorplot(x="FamilyCategory", hue="Survived", data=tmp_df, kind="count", size=6)
sns.FacetGrid(tmp_df, row="Survived",size=8).map(sns.kdeplot, "Age").add_legend()

titanic_all.drop(['PassengerId', 'Name', 'Cabin','Ticket','Survived'], axis=1, inplace=True)

features = ['Sex', 'Embarked', 'Pclass', 'Title', 'FamilyCategory']
titanic_all = pd.get_dummies(titanic_all, columns=features)

X_train = titanic_all[0:titanic_train.shape[0]]
y_train = titanic_train['Survived']

#applying feature selection algorithm to get impactful features
rf = ensemble.RandomForestClassifier(n_estimators=100), y_train)
github pysal / pysal / pysal / viz / splot / View on Github external
    # to set default as an empty dictionary that is later filled with defaults
    if fitline_kwds is None:
        fitline_kwds = dict()

    figsize = kwargs.pop('figsize', (7, 7))
    # get fig and ax
    fig, ax = _create_moran_fig_ax(ax, figsize)

    # plot distribution
    shade = kwargs.pop('shade', True)
    color = kwargs.pop('color', splot_colors['moran_base'])
    sbn.kdeplot(moran.sim, shade=shade, color=color, ax=ax, **kwargs)

    # customize plot
    fitline_kwds.setdefault('color', splot_colors['moran_fit'])
    ax.vlines(moran.I, 0, 1, **fitline_kwds)
    ax.vlines(moran.EI, 0, 1)
    ax.set_title('Reference Distribution')
    ax.set_xlabel('Moran I: ' + str(round(moran.I, 2)))
    return fig, ax
github aleju / gan-error-avoidance / g_lis / View on Github external

    codes = torch.randn(opt.nb_points, opt.code_size).cuda()
    for r_idx in range(1+opt.r_iterations):
        codes_r_2d = embed_or_load_cache(codes, gen, r_idx, opt.batch_size, opt.save_path)

        fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(10, 10))
        ax.scatter(codes_r_2d[:, 0], codes_r_2d[:, 1], s=2, alpha=0.2)
        ax.set_xlim((-10, 10))
        ax.set_ylim((-10, 10))
        fig.savefig(os.path.join(opt.save_path, 'tsne_plots', 'tsne_%04d_r%02d.jpg' % (0, r_idx,)))

        fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(10, 10))
        sns_plot = sns.kdeplot(codes_r_2d[:, 0], codes_r_2d[:, 1], shade=True, ax=ax)
        sns_plot.axes.set_xlim((-10, 10))
        sns_plot.axes.set_ylim((-10, 10))
        fig = sns_plot.get_figure()
        fig.savefig(os.path.join(opt.save_path, 'tsne_plots', 'tsne_%04d_r%02d_kde.jpg' % (0, r_idx,)))
github wuga214 / NCE_Projected_LRec / plots / View on Github external
def pandas_ridge_plot(df, model, pop, k, folder='figures', name='personalization', save=True):
    sns.set(style="white", rc={"axes.facecolor": (0, 0, 0, 0)})
    num_models = len(df.model.unique())

    # Initialize the FacetGrid object
    pal = sns.cubehelix_palette(num_models, rot=-.25, light=.7)
    g = sns.FacetGrid(df, row=model, hue=model, aspect=10, height=1, palette=pal)

    # Draw the densities in a few steps, pop, clip_on=False, shade=True, alpha=1, lw=1.5, bw=50), pop, clip_on=False, color="w", lw=1.5, bw=50), y=0, lw=2, clip_on=False)

    # Define and use a simple function to label the plot in axes coordinates
    def label(x, color, label):
        ax = plt.gca()
        ax.text(-0.1, .1, label, fontweight="bold", color=color,
                ha="left", va="center", transform=ax.transAxes), pop)

    # Set the subplots to overlap

    # Remove axes details that don't play well with overlap

    g.set_xlabels("Popularity Distribution of The Top-{0} Recommended Items".format(k))
github astrazeneca-cgr-publications / mantis-ml-release / mantis_ml / modules / pre_processing / View on Github external
if i in cols_for_log_plus_one:
                tmp_df.iloc[:, 0] = np.log(df[i] + 1)

            pos_tmp_df = tmp_df.loc[tmp_df[self.cfg.Y].astype(float) == 1, i]
            pos_tmp_df.rename(pos_label, inplace=True)

            neg_tmp_df = tmp_df.loc[tmp_df[self.cfg.Y].astype(float) == 0, i]
            neg_tmp_df.rename(neg_label, inplace=True)

                sns.kdeplot(pos_tmp_df, shade=True, color="#fb6a4a")
                sns.kdeplot(neg_tmp_df, shade=True, color="#3182bd")

        plot_filepath = str(self.cfg.eda_out / 'numerical_features_histograms.pdf')
        fig.savefig(plot_filepath, format='pdf', bbox_inches='tight')
github lucasrodes / whatstk / View on Github external
def chat_scatter_matrix_density(data):
    g = sns.PairGrid(data, diag_sharey=False)
    g.map_lower(sns.kdeplot, cmap="Blues_d")
    g.map_diag(sns.kdeplot, lw=3)
    plt.title(r'Scatter plot together with estimated pair densities')
    # plt.suptitle(r""+title, fontsize=18)
github mattdonders / nhl-twitter-bot / View on Github external
# Build Plot (via Matplotlib)
    MY_DPI = 96
    IMG_WIDTH = 1024
    IMG_HEIGHT = 440
    fig = plt.figure(figsize=(FIG_WIDTH, FIG_HEIGHT), dpi=MY_DPI)
    ax = fig.add_subplot(111)

    ax_extent = [-100, 100, -42.5, 42.5]
    img =, 'resources/images/Rink-Shotmap-Blank.png'))
    ax.imshow(img, extent=ax_extent)

    # Draw the heatmap portion of the graph
    sns.kdeplot(pref_df.coords_x, pref_df.coords_y, cmap='Reds', shade=True, bw=0.2, cut=100, shade_lowest=False, alpha=0.9, ax=ax)
    sns.kdeplot(other_df.coords_x, other_df.coords_y, cmap="Blues", shade=True, bw=0.2, cut=100, shade_lowest=False, alpha=0.9, ax=ax)

    # Draw the goal markers
    if not pref_goals_df.empty:
        ax.scatter(pref_goals_df.coords_x, pref_goals_df.coords_y, marker='*', s=30, c='#333333')
    if not other_goals_df.empty:
        ax.scatter(other_goals_df.coords_x, other_goals_df.coords_y, marker='*', s=30, c='#333333')

    if not pref_ppg_df.empty:
        ax.scatter(pref_ppg_df.coords_x, pref_ppg_df.coords_y, marker='^', s=30, c='#333333')
    if not other_ppg_df.empty:
        ax.scatter(other_ppg_df.coords_x, other_ppg_df.coords_y, marker='^', s=30, c='#333333')

    # Draw the shot markers (40% opacity)
    ax.scatter(pref_shots_df.coords_x, pref_shots_df.coords_y, marker='o', s=10, c='#333333', alpha=0.4)
    ax.scatter(other_shots_df.coords_x, other_shots_df.coords_y, marker='o', s=10, c='#333333', alpha=0.4)
github StructuralNeurobiologyLab / SyConn / syconn / proc / View on Github external
    plt.ylabel('$Z_2$', fontsize=15)
    plt.xlabel('$Z_1$', fontsize=15)
    if colors is None:
        # colors = ["r", "g", "b", "y", "k"]
        if len(target_names) == 5:
            colors = ["r", "g", "b", "y", "k"]
            cmap ="Accent", len(target_names))
            colors = [cmap(i) for i in range(len(target_names))]
    if target_names is None:
        target_names = ["%d" % i for i in nb_labels]
    for i in nb_labels:
        cur_pal = sns.light_palette(colors[i], as_cmap=True)
        d0, d1 = res[ds_l == i][:, 0], res[ds_l == i][:, 1]
        ax = sns.kdeplot(d0, d1, shade=False, cmap=cur_pal,
                         alpha=0.6, shade_lowest=False, gridsize=100)
        plt.scatter(res[ds_l == i][:, 0], res[ds_l == i][:, 1],
                                s=1.2, lw=0, alpha=0.5, color=colors[i], label=target_names[i])
    handles = []
    for ii in range(len(target_names)):
        handles.append(mpatches.Patch(color=colors[ii], label=target_names[ii]))
    plt.legend(handles=handles, loc="best")
    plt.savefig(dest_path, dpi=300)
    if do_3d:
        # density plot 1st and 3rd PC
        plt.ylabel('$Z_3$', fontsize=15)
        plt.xlabel('$Z_1$', fontsize=15)
github algorithmica-repository / datascience / 2017-feb / 3.eda / View on Github external
#explore univariate continuous feature
print titanic_train['Fare'].mean()
print titanic_train['Fare'].median()
print titanic_train['Fare'].quantile(0.25)
print titanic_train['Fare'].quantile(0.75)
print titanic_train['Fare'].std()


#explore univariate continuous features visually
sns.distplot(titanic_train['Fare'], bins=20, rug=True, kde=False)
sns.distplot(titanic_train['Fare'], bins=100, kde=False)
sns.kdeplot(data=titanic_train['Fare'], shade=True)

#explore univariate categorical feature
pd.crosstab(index=titanic_train["Survived"], columns="count")
pd.crosstab(index=titanic_train["Pclass"], columns="count")  
pd.crosstab(index=titanic_train["Sex"],  columns="count")

#explore univariate categorical features visually
github kmkolasinski / deep-learning-notes / IIC / View on Github external
    prediction_dict = defaultdict(list)

    for i in range(num_steps):
        features, labels = next(dataset_iterator)
        p_out_preds = iic_model.predict(features, steps=None)
        if type(p_out_preds) == np.ndarray:
            p_out_preds = [p_out_preds]

        for k, p_out in enumerate(p_out_preds):
            prediction_dict[f"y_pred_{k}"] += p_out.argmax(-1).tolist()
        prediction_dict[f"y_true"] += labels["label"].numpy().tolist()

    df = pd.DataFrame(prediction_dict)
    g = sns.PairGrid(df)
    return g.map_offdiag(sns.kdeplot, n_levels=6)