d3graph 2.6.2__tar.gz → 2.7.2__tar.gz

{d3graph-2.6.2/d3graph.egg-info → d3graph-2.7.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: d3graph
-Version: 2.6.2
+Version: 2.7.2
 Summary: Python package to create interactive network based on d3js.
 Author-email: Erdogan Taskesen <erdogant@gmail.com>
 License-Expression: BSD-3-Clause
@@ -24,7 +24,7 @@ Requires-Dist: networkx>2
 Requires-Dist: ismember
 Requires-Dist: jinja2
 Requires-Dist: packaging
-Requires-Dist: markupsafe==2.0.1
+Requires-Dist: markupsafe
 Requires-Dist: python-louvain
 Requires-Dist: datazets
 Dynamic: license-file

{d3graph-2.6.2 → d3graph-2.7.2}/d3graph/__init__.py

@@ -11,11 +11,13 @@ from d3graph.d3graph import (
     adjmat2dict,
     data_checks,
     check_logger,
+    get_hex_color,
+    import_example,
     )
 
 __author__ = 'Erdogan Tasksen'
 __email__ = 'erdogant@gmail.com'
-__version__ = '2.6.2'
+__version__ = '2.7.2'
 
 # Setup root logger
 _logger = logging.getLogger('d3graph')
@@ -39,13 +41,13 @@ The ouput is a html file that is interactive and stand alone.
 
 Examples
 --------
->>> from d3graph import d3graph, vec2adjmat
+>>> from d3graph import d3graph, vec2adjmat, import_example
 >>>
 >>> # Initialize
 >>> d3 = d3graph()
 >>>
 >>> # Load karate example
->>> df = d3.import_example('energy')
+>>> df = import_example('energy')
 >>> adjmat = vec2adjmat(source=df['source'], target=df['target'], weight=df['weight'])
 >>>
 >>> # Initialize
@@ -63,7 +65,6 @@ Examples
 References
 ----------
 * D3Graph: erdogant.medium.com
-* D3Blocks: https://medium.com/data-science-collective/d3blocks-the-python-library-to-create-interactive-standalone-and-beautiful-d3-js-charts-ef8c65286e86
 * Github : https://github.com/erdogant/d3graph
 * Documentation: https://erdogant.github.io/d3graph/
 

{d3graph-2.6.2 → d3graph-2.7.2}/d3graph/d3graph.py

@@ -12,7 +12,7 @@ import webbrowser
 from json import dumps
 from pathlib import Path
 from sys import platform
-from tempfile import TemporaryDirectory, gettempdir
+from tempfile import gettempdir
 from unicodedata import normalize
 import uuid
 
@@ -21,15 +21,13 @@ import colourmap as cm
 import networkx as nx
 import numpy as np
 import pandas as pd
+from pandas.arrays import StringArray
 from ismember import ismember
 from jinja2 import Environment, PackageLoader
 from packaging import version
 import datazets as dz
 
 logger = logging.getLogger(__name__)
-if not logger.hasHandlers():
-    logging.basicConfig(level=logging.INFO, format='[{asctime}] [{name}] [{levelname}] {msg}', style='{', datefmt='%d-%m-%Y %H:%M:%S')
-
 
 # %%
 class d3graph:
@@ -58,8 +56,7 @@ class d3graph:
 
     References
     ----------
-    * D3Graph: https://erdogant.medium.com/
-    * D3Blocks: https://medium.com/data-science-collective/d3blocks-the-python-library-to-create-interactive-standalone-and-beautiful-d3-js-charts-ef8c65286e86
+    * Medium: https://erdogant.medium.com/
     * Github : https://github.com/erdogant/d3graph
     * Documentation: https://erdogant.github.io/d3graph/
 
@@ -70,8 +67,17 @@ class d3graph:
                  charge: int = 600,
                  slider=None,
                  support: str = 'text',
+                 link_tension: float = 1,
+                 sticky: bool = True,
                  verbose: int = 20) -> None:
-        """Initialize d3graph."""
+        """Initialize d3graph.
+
+        Parameters (additional to existing)
+        ------------------------------------
+        sticky : bool, (default: False)
+            When True, nodes stay fixed in place after being dragged.
+            Right-click a fixed node to release it back into the simulation.
+        """
         if slider is None: slider = [None, None]
         # Cleaning
         self._clean()
@@ -85,6 +91,8 @@ class d3graph:
         self.config['charge'] = -abs(charge)
         self.config['slider'] = slider
         self.config['support'] = get_support(support)
+        self.config['link_tension'] = link_tension
+        self.config['sticky'] = sticky
         # Set paths
         self.config['curpath'] = os.path.dirname(os.path.abspath(__file__))
         self.config['d3_library'] = os.path.abspath(os.path.join(self.config['curpath'], 'd3js/d3.v3.js'))
@@ -110,6 +118,8 @@ class d3graph:
              dark_mode = False,
              notebook: bool = False,
              save_button: bool = True,
+             link_tension: float = None,
+             sticky: bool = None,
              ) -> None:
         """Build and show the graph.
 
@@ -150,6 +160,11 @@ class d3graph:
         save_button : bool, (default: True)
             True: Save button is shown in the HTML to save the image in svg.
             False: No save button is shown in the HTML.
+        sticky : bool, (default: None)
+            When True, nodes stay fixed in place after being dragged (overrides the value set in __init__).
+            When False, nodes are released after dragging (default simulation behaviour).
+            When None, the value set in __init__ is used.
+            Right-click a fixed node to release it back into the simulation.
 
         Returns
         -------
@@ -171,8 +186,15 @@ class d3graph:
         self.config['save_button'] = save_button
         self.config['background_color'] = background_color
         self.config['dark_mode'] = dark_mode
+        # Allow show() to override the link_tension set at __init__ time
+        if link_tension is not None:
+            self.config['link_tension'] = link_tension
+        # Override sticky only when explicitly passed
+        if sticky is not None:
+            self.config['sticky'] = sticky
         # if self.config.get('filepath', None) != 'd3graph.html':
-        self.config['filepath'] = self.set_path(filepath)
+        if filepath is not None or self.config.get('filepath') is None:
+            self.set_path(filepath)
 
         # Create dataframe from co-occurrence matrix
         self.G = make_graph(self.node_properties, self.edge_properties)
@@ -308,6 +330,10 @@ class d3graph:
         self.config['label'] = label
         self.config['label_color'] = label_color
         self.config['label_fontsize'] = label_fontsize
+        
+        if not hasattr(self, 'adjmat'):
+            logger.error('adjmat is missing. Initialize first with d3 = d3graph(adjmat)')
+            return
 
         if (not directed) and (marker_end is not None) or (marker_start is not None):
             logger.info('Set directed=True to see the markers!')
@@ -447,18 +473,22 @@ class d3graph:
                 'edge_color': edge_color of the node
 
         """
+        if not hasattr(self, 'adjmat'):
+            logger.error('adjmat is missing. Initialize first with d3 = d3graph(adjmat)')
+            return
+
         if minmax is None: minmax = [8, 13]
         node_names = self.adjmat.columns.astype(str)
         nodecount = self.adjmat.shape[0]
         group = np.zeros_like(node_names).astype(int)
         # Check validity of color.
-        _check_hex_color(color, nodecount)
+        color = _check_hex_color(color, nodecount, cmap=cmap)
         # Store in config
         self.config['cmap'] = 'Paired' if cmap is None else cmap
         self.config['node_scaler'] = scaler
 
         # ############ Set node label #############
-        if isinstance(label, list):
+        if isinstance(label, (list, np.ndarray, pd.Series, pd.Series, StringArray)):
             label = np.array(label).astype(str)
         elif 'numpy' in str(type(label)):
             pass
@@ -471,7 +501,7 @@ class d3graph:
         if len(label) != nodecount: raise ValueError("[label] must be of same length as the number of nodes")
 
         # ############ tooltip text #############
-        if isinstance(tooltip, list):
+        if isinstance(tooltip, (list, np.ndarray, pd.Series, StringArray)):
             tooltip = np.array(tooltip).astype(str)
         elif 'numpy' in str(type(tooltip)):
             pass
@@ -484,7 +514,7 @@ class d3graph:
         if len(tooltip) != nodecount: raise ValueError("[tooltip text] must be of same length as the number of nodes")
 
         # ############ Set node color #############
-        if isinstance(color, list) and len(color) == nodecount:
+        if isinstance(color, (list, np.ndarray, pd.Series, StringArray)) and len(color) == nodecount:
             color = np.array(color)
         elif 'numpy' in str(type(color)):
             color = _get_hexcolor(color, cmap=self.config['cmap'])
@@ -514,7 +544,7 @@ class d3graph:
         fontsize = _set_node_fontsize(self, fontsize, nodecount)
 
         # ########## Set node color edge #############
-        if isinstance(edge_color, list):
+        if isinstance(edge_color, (list, np.ndarray, pd.Series, StringArray)):
             edge_color = np.array(edge_color)
         elif 'numpy' in str(type(edge_color)):
             pass
@@ -546,7 +576,7 @@ class d3graph:
         marker = _set_marker(self, marker, nodecount)
 
         # ############ Set node edge size #############
-        if isinstance(edge_size, list):
+        if isinstance(edge_size, (list, np.ndarray, pd.Series, StringArray)):
             edge_size = np.array(edge_size)
         elif 'numpy' in str(type(edge_size)):
             pass
@@ -569,16 +599,16 @@ class d3graph:
                                           'marker': marker[i],
                                           'label': label[i],
                                           'tooltip': tooltip[i],
-                                          'color': color[i].astype(str),
-                                          'opacity': opacity[i].astype(str),
-                                          'fontcolor': fontcolor[i].astype(str),
-                                          'fontsize': fontsize[i].astype(int),
+                                          'color': str(color[i]),
+                                          'opacity': str(opacity[i]),
+                                          'fontcolor': str(fontcolor[i]),
+                                          'fontsize': str(fontsize[i]),
                                           'size': size[i],
                                           'edge_size': edge_size[i],
                                           'edge_color': edge_color[i],
                                           'group': group[i]}
 
-        logger.info('Number of unique nodes: %.0d', len(self.node_properties.keys()))
+        logger.info(f'Number of unique nodes: {len(self.node_properties.keys())}')
 
     # compute clusters
     def get_cluster_color(self, node_names: list = None, color: str = '#000080') -> tuple:
@@ -685,13 +715,13 @@ class d3graph:
 
         Examples
         --------
-        >>> from d3graph import d3graph
+        >>> from d3graph import d3graph, import_example
         >>>
         >>> # Initialize
         >>> d3 = d3graph()
         >>>
         >>> # Load karate example
-        >>> adjmat, df = d3.import_example('karate')
+        >>> adjmat, df = import_example('karate')
         >>>
         >>> # Initialize
         >>> d3.graph(adjmat)
@@ -763,6 +793,8 @@ class d3graph:
                    'max_slider': self.config['slider'][1],
                    'directed': self.config['directed'],
                    'collision': self.config['collision'],
+                   'link_tension': self.config.get('link_tension', 1.0),
+                   'sticky': self.config.get('sticky', False),
                    'CLICK_COMMENT': CLICK_COMMENT,
                    'CLICK_FILL': click_properties['fill'],
                    'CLICK_STROKE': click_properties['stroke'],
@@ -833,7 +865,8 @@ class d3graph:
         os.makedirs(dirname, exist_ok=True)
         filepath = os.path.abspath(os.path.join(dirname, filename))
         logger.debug(f'filepath is set to [{filepath}]')
-        return Path(filepath)
+        # Set to config
+        self.config['filepath'] = Path(filepath)
 
     def import_example(self, data='energy', url=None, sep=','):
         """Import example dataset from github source.
@@ -857,38 +890,7 @@ class d3graph:
             * https://github.com/erdogant/datazets
 
         """
-        if data == 'small':
-            source = ['node A', 'node F', 'node B', 'node B', 'node B', 'node A', 'node C', 'node Z']
-            target = ['node F', 'node B', 'node J', 'node F', 'node F', 'node M', 'node M', 'node A']
-            weight = [5.56, 0.5, 0.64, 0.23, 0.9, 3.28, 0.5, 0.45]
-            adjmat = vec2adjmat(source, target, weight=weight)
-            return adjmat, None
-        elif data == 'bigbang':
-            df = dz.get(data=data)
-            adjmat = vec2adjmat(df['source'], df['target'], weight=df['weight'])
-            return adjmat
-        elif data == 'karate':
-            import scipy
-            if version.parse(scipy.__version__) < version.parse('1.8.0'):
-                raise ImportError(
-                    '[d3graph] >Error: This release requires scipy version >= 1.8.0. Try: pip install -U scipy>=1.8.0')
-
-            G = nx.karate_club_graph()
-            adjmat = nx.adjacency_matrix(G).todense()
-            adjmat = pd.DataFrame(index=range(adjmat.shape[0]), data=adjmat, columns=range(adjmat.shape[0]))
-            adjmat.columns = adjmat.columns.astype(str)
-            adjmat.index = adjmat.index.astype(str)
-            adjmat.iloc[3, 4] = 5
-            adjmat.iloc[4, 5] = 6
-            adjmat.iloc[5, 6] = 7
-
-            df = pd.DataFrame(index=adjmat.index)
-            df['degree'] = np.array([*G.degree()])[:, 1]
-            df['label'] = [G.nodes[i]['club'] for i in range(len(G.nodes))]
-
-            return adjmat, df
-        else:
-            return dz.get(data=data, url=url, sep=sep)
+        return import_example(data=data, url=url, sep=sep)
 
 
 # %%
@@ -1193,6 +1195,7 @@ def adjmat2dict(adjmat: pd.DataFrame,
     df['label_color']=label_color
     df['label_fontsize']=label_fontsize
     df['edge_style']=edge_style
+    df['edge_color']=edge_color
     df['edge_opacity'] = edge_opacity
     df['tooltip'] = df['weight'].astype(str)
 
@@ -1357,6 +1360,7 @@ def _normalize_size(getsizes, minscale=0.5, maxscale=4, scaler: str = 'zscore'):
     # Instead of Min-Max scaling, that shrinks any distribution in the [0, 1] interval, scaling the variables to
     # Z-scores is better. Min-Max Scaling is too sensitive to outlier observations and generates unseen problems.
 
+    getsizes = getsizes.copy()
     # Set sizes to 0 if not available
     getsizes[np.isinf(getsizes)]=0
     getsizes[np.isnan(getsizes)]=0
@@ -1395,6 +1399,8 @@ def _get_hexcolor(label, cmap: str = 'Paired'):
 
     return label
 
+def get_hex_color(labels, cmap='Set1', opaque_type='per_class', gradient=None):
+    return cm.fromlist(labels, scheme='hex', opaque_type=opaque_type, gradient=gradient)
 
 # %% Do checks
 def library_compatibility_checks() -> None:
@@ -1591,15 +1597,21 @@ def adjmat2vec(adjmat, min_weight: float = 1.0) -> pd.DataFrame:
     return adjmat
 
 
-def _check_hex_color(color, n=None):
-    if isinstance(color, str) and len(color) != 7: raise ValueError(
-        'Input parameter [color] has wrong format. Must be like color="#000000"')
-    if isinstance(color, list) and len(color) == 0: raise ValueError(
-        'Input parameter [color] has wrong format and length. Must be like: color=["#000000", "...", "#000000"]')
-    if isinstance(color, list) and (not np.all(list(map(lambda x: len(x) == 7, color)))): raise ValueError(
-        '[color] contains incorrect length of hex-color! Hex must be of length 7: ["#000000", "#000000", etc]')
-    if (n is not None) and isinstance(color, list) and len(color) != n:
-        raise ValueError(f'Input parameter [color] has wrong length. Must be of length: {str(n)}')
+def _check_hex_color(color, n=None, cmap='Set1'):
+    if isinstance(color, str) and len(color) != 7:
+        logger.warning('Input parameter [color] has wrong format. Must be like color="#000000" <auto-fixing>')
+        return get_hex_color(color, cmap=cmap)[0]
+    if isinstance(color, (list, np.ndarray, pd.Series, pd.Series, StringArray)) and len(color) == 0:
+        logger.warning('Input parameter [color] has wrong format and length. Must be like: color=["#000000", "...", "#000000"] <auto-fixing>')
+        return get_hex_color(color, cmap=cmap)[0]
+    if isinstance(color, (list, np.ndarray, pd.Series, pd.Series, StringArray)) and (not np.all(list(map(lambda x: len(x) == 7, color)))):
+        logger.warning('[color] contains incorrect hex-colors. Hex must be of length 7: ["#000000", "#000000", etc] <auto-fixing>')
+        return get_hex_color(color, cmap=cmap)[0]
+    if (n is not None) and isinstance(color, (list, np.ndarray, pd.Series, pd.Series, StringArray)) and len(color) != n:
+        logger.warning(f'Input parameter [color] has wrong length. Must be of length: {str(n)} <auto-fixing>')
+        return get_hex_color(color, cmap=cmap)[0]
+    # Return original input
+    return color
 
 
 def _set_opacity(self, opacity, nodecount, node_names):
@@ -1723,6 +1735,61 @@ def _set_node_fontcolor(self, fontcolor, color, node_names, nodecount):
     # return
     return fontcolor
 
+def import_example(data='energy', url=None, sep=','):
+    """Import example dataset from github source.
+
+    Import one of the few datasets from github source or specify your own download url link.
+
+    Parameters
+    ----------
+    data : str
+        Name of datasets: 'sprinkler', 'titanic', 'student', 'fifa', 'cancer', 'waterpump', 'retail'
+    url : str
+        url link to to dataset.
+
+    Returns
+    -------
+    pd.DataFrame()
+        Dataset containing mixed features.
+
+    References
+    ----------
+        * https://github.com/erdogant/datazets
+
+    """
+    if data == 'small':
+        source = ['node A', 'node F', 'node B', 'node B', 'node B', 'node A', 'node C', 'node Z']
+        target = ['node F', 'node B', 'node J', 'node F', 'node F', 'node M', 'node M', 'node A']
+        weight = [5.56, 0.5, 0.64, 0.23, 0.9, 3.28, 0.5, 0.45]
+        adjmat = vec2adjmat(source, target, weight=weight)
+        return adjmat, None
+    elif data == 'bigbang':
+        df = dz.get(data=data)
+        adjmat = vec2adjmat(df['source'], df['target'], weight=df['weight'])
+        return adjmat
+    elif data == 'karate':
+        import scipy
+        if version.parse(scipy.__version__) < version.parse('1.8.0'):
+            raise ImportError(
+                '[d3graph] >Error: This release requires scipy version >= 1.8.0. Try: pip install -U scipy>=1.8.0')
+
+        G = nx.karate_club_graph()
+        adjmat = nx.adjacency_matrix(G).todense()
+        adjmat = pd.DataFrame(index=range(adjmat.shape[0]), data=adjmat, columns=range(adjmat.shape[0]))
+        adjmat.columns = adjmat.columns.astype(str)
+        adjmat.index = adjmat.index.astype(str)
+        adjmat.iloc[3, 4] = 5
+        adjmat.iloc[4, 5] = 6
+        adjmat.iloc[5, 6] = 7
+
+        df = pd.DataFrame(index=adjmat.index)
+        df['degree'] = np.array([*G.degree()])[:, 1]
+        df['label'] = [G.nodes[i]['club'] for i in range(len(G.nodes))]
+
+        return adjmat, df
+    else:
+        return dz.get(data=data, url=url, sep=sep)
+
 
 def get_support(support):
     """Support."""
@@ -1734,4 +1801,4 @@ def get_support(support):
         script = script + '\n' + "<div data-ea-publisher='erdogantgithubio' data-ea-type='{TYPE}' data-ea-style='stickybox'></div>".replace('{TYPE}', support)
 
     # Return
-    return script
+    return script