1.7.5

 - #64, handling for loading duplicate data to dtale.show
 - updated dtale.instances() to print urls rather than show all instances
 - removal of Dash "Export to png" function
 - passing data grid queries to chart page as default
 - added sys.exit() to the thread that manages the reaper

README.md

@@ -18,6 +18,10 @@ D-Tale is the combination of a Flask back-end and a React front-end to bring you
 
 D-Tale was the product of a SAS to Python conversion.  What was originally a perl script wrapper on top of SAS's `insight` function is now a lightweight web client on top of Pandas data structures.
 
+## In The News
+ - [Man Institute](https://www.man.com/maninstitute/d-tale)
+ - [Python Bytes](https://pythonbytes.fm/episodes/show/169/jupyter-notebooks-natively-on-your-ipad)
+
 ## Contents
 
 - [Getting Started](#getting-started)
@@ -102,6 +106,15 @@ dtale.instances()  # returns a dictionary of all instances available, this would
 
 ```
 
+#### Duplicate data check
+To help guard against users loading the same data to D-Tale multiple times and thus eating up precious memory, we have a loose check for duplicate input data.  The check runs the following:
+ * Are row & column count the same as a previously loaded piece of data?
+ * Are the names and order of columns the same as a previously loaded piece of data?
+
+If both these conditions are true then you will be presented with an error and a link to the previously loaded data.  Here is an example of how the interaction looks:
+![](https://raw.githubusercontent.com/aschonfeld/dtale-media/master/images/Duplicate_data.png)
+
+
 ### Jupyter Notebook
 Within any jupyter (ipython) notebook executing a cell like this will display a small instance of D-Tale in the output cell.  Here are some examples:
 

dtale/app.py

@@ -21,8 +21,8 @@
 
 from dtale import dtale
 from dtale.cli.clickutils import retrieve_meta_info_and_version, setup_logging
-from dtale.utils import (build_shutdown_url, build_url, dict_merge, get_host,
-                         running_with_flask_debug)
+from dtale.utils import (DuplicateDataError, build_shutdown_url, build_url,
+                         dict_merge, get_host, running_with_flask_debug)
 from dtale.views import (DATA, DtaleData, cleanup, head_data_id, is_up, kill,
                          startup)
 
@@ -93,6 +93,7 @@ def __init__(self, import_name, reaper_on=True, url=None, *args, **kwargs):
         """
         self.reaper_on = reaper_on
         self.reaper = None
+        self.base_url = url
         self.shutdown_url = build_shutdown_url(url)
         self.port = None
         super(DtaleFlask, self).__init__(import_name, *args, **kwargs)
@@ -146,7 +147,9 @@ def build_reaper(self, timeout=REAPER_TIMEOUT):
 
         def _func():
             logger.info('Executing shutdown due to inactivity...')
-            requests.get(self.shutdown_url)
+            if is_up(self.base_url):  # make sure the Flask process is still running
+                requests.get(self.shutdown_url)
+            sys.exit()  # kill off the reaper thread
 
         self.reaper = Timer(timeout, _func)
         self.reaper.start()
@@ -394,7 +397,8 @@ def is_port_in_use(port):
 
 
 def show(data=None, host=None, port=None, name=None, debug=False, subprocess=True, data_loader=None,
-         reaper_on=True, open_browser=False, notebook=False, force=False, context_vars=None, **kwargs):
+         reaper_on=True, open_browser=False, notebook=False, force=False, context_vars=None, ignore_duplicate=False,
+         **kwargs):
     """
     Entry point for kicking off D-Tale :class:`flask:flask.Flask` process from python process
 
@@ -426,6 +430,9 @@ def show(data=None, host=None, port=None, name=None, debug=False, subprocess=Tru
     :param context_vars: a dictionary of the variables that will be available for use in user-defined expressions,
                          such as filters
     :type context_vars: dict, optional
+    :param ignore_duplicate: if true, this will not check if this data matches any other data previously loaded to
+                             D-Tale
+    :type ignore_duplicate: bool, optional
 
     :Example:
 
@@ -438,59 +445,67 @@ def show(data=None, host=None, port=None, name=None, debug=False, subprocess=Tru
         ..link displayed in logging can be copied and pasted into any browser
     """
 
-    logfile, log_level, verbose = map(kwargs.get, ['logfile', 'log_level', 'verbose'])
-    setup_logging(logfile, log_level or 'info', verbose)
-
-    initialize_process_props(host, port, force)
-    url = build_url(ACTIVE_PORT, ACTIVE_HOST)
-    instance = startup(url, data=data, data_loader=data_loader, name=name, context_vars=context_vars)
-    is_active = not running_with_flask_debug() and is_up(url)
-    if is_active:
-        def _start():
-            if open_browser:
-                instance.open_browser()
-    else:
-        def _start():
-            app = build_app(url, reaper_on=reaper_on, host=ACTIVE_HOST)
-            if debug:
-                app.jinja_env.auto_reload = True
-                app.config['TEMPLATES_AUTO_RELOAD'] = True
-            else:
-                getLogger("werkzeug").setLevel(LOG_ERROR)
-
-            if open_browser:
-                instance.open_browser()
-
-            # hide banner message in production environments
-            cli = sys.modules.get('flask.cli')
-            if cli is not None:
-                cli.show_server_banner = lambda *x: None
+    try:
+        logfile, log_level, verbose = map(kwargs.get, ['logfile', 'log_level', 'verbose'])
+        setup_logging(logfile, log_level or 'info', verbose)
 
-            app.run(host='0.0.0.0', port=ACTIVE_PORT, debug=debug, threaded=True)
-
-    if subprocess:
+        initialize_process_props(host, port, force)
+        url = build_url(ACTIVE_PORT, ACTIVE_HOST)
+        instance = startup(url, data=data, data_loader=data_loader, name=name, context_vars=context_vars,
+                           ignore_duplicate=ignore_duplicate)
+        is_active = not running_with_flask_debug() and is_up(url)
         if is_active:
-            _start()
+            def _start():
+                if open_browser:
+                    instance.open_browser()
         else:
-            _thread.start_new_thread(_start, ())
+            def _start():
+                app = build_app(url, reaper_on=reaper_on, host=ACTIVE_HOST)
+                if debug:
+                    app.jinja_env.auto_reload = True
+                    app.config['TEMPLATES_AUTO_RELOAD'] = True
+                else:
+                    getLogger("werkzeug").setLevel(LOG_ERROR)
+
+                if open_browser:
+                    instance.open_browser()
+
+                # hide banner message in production environments
+                cli = sys.modules.get('flask.cli')
+                if cli is not None:
+                    cli.show_server_banner = lambda *x: None
+
+                app.run(host='0.0.0.0', port=ACTIVE_PORT, debug=debug, threaded=True)
+
+        if subprocess:
+            if is_active:
+                _start()
+            else:
+                _thread.start_new_thread(_start, ())
 
-        if notebook:
-            instance.notebook()
-    else:
-        logger.info('D-Tale started at: {}'.format(url))
-        _start()
+            if notebook:
+                instance.notebook()
+        else:
+            logger.info('D-Tale started at: {}'.format(url))
+            _start()
 
-    return instance
+        return instance
+    except DuplicateDataError as ex:
+        print(
+            'It looks like this data may have already been loaded to D-Tale based on shape and column names. Here is '
+            'URL of the data that seems to match it:\n\n{}\n\nIf you still want to load this data please use the '
+            'following command:\n\ndtale.show(df, ignore_duplicate=True)'.format(
+                DtaleData(ex.data_id, build_url(ACTIVE_PORT, ACTIVE_HOST)).main_url()
+            )
+        )
+    return None
 
 
 def instances():
     """
-    Returns a dictionary of data IDs & :class:`dtale.views.DtaleData` objects pertaining to all the current pieces of
-    data being viewed
-
-    :return: dict
+    Prints all urls to the current pieces of data being viewed
     """
-    return {data_id: DtaleData(data_id, build_url(ACTIVE_PORT, ACTIVE_HOST)) for data_id in DATA}
+    print('\n'.join([DtaleData(data_id, build_url(ACTIVE_PORT, ACTIVE_HOST)).main_url() for data_id in DATA]))
 
 
 def get_instance(data_id):

dtale/dash_application/charts.py

@@ -21,7 +21,7 @@
 from dtale.utils import (classify_type, dict_merge, divide_chunks,
                          flatten_lists, get_dtypes, make_list,
                          make_timeout_request, run_query)
-from dtale.views import DATA, CONTEXT_VARIABLES
+from dtale.views import CONTEXT_VARIABLES, DATA
 from dtale.views import build_chart as build_chart_data
 
 

dtale/dash_application/layout.py

@@ -283,13 +283,16 @@ def show_yaxis_ranges(**inputs):
     return chart_type in YAXIS_CHARTS and len(y or [])
 
 
-def charts_layout(df, **inputs):
+def charts_layout(df, settings, **inputs):
     """
     Builds main dash inputs with dropdown options populated with the columns of the dataframe associated with the
     page. Inputs included are: chart tabs, query, x, y, z, group, aggregation, rolling window/computation,
     chart per group toggle, bar sort, bar mode, y-axis range editors
 
     :param df: dataframe to drive the charts built on page
+    :type df: :class:`pandas:pandas.DataFrame`
+    :param settings: global settings associated with this dataframe (contains properties like "query")
+    :type param: dict
     :return: dash markup
     """
     [chart_type, x, y, z, group, agg] = [inputs.get(p) for p in ['chart_type', 'x', 'y', 'z', 'group', 'agg']]
@@ -327,7 +330,7 @@ def charts_layout(df, **inputs):
             html.Div([
                 query_label, dcc.Input(
                     id='query-input', type='text', placeholder=query_placeholder, className='form-control',
-                    value=inputs.get('query'), style={'line-height': 'inherit'})
+                    value=inputs.get('query') or settings.get('query'), style={'line-height': 'inherit'})
             ], className='input-group mr-3')],
             className='col'
         ), className='row pt-3 pb-3 charts-filters'),

dtale/dash_application/views.py

@@ -17,7 +17,7 @@
                                            show_input_handler,
                                            show_yaxis_ranges)
 from dtale.utils import dict_merge, make_list, run_query
-from dtale.views import DATA, CONTEXT_VARIABLES
+from dtale.views import CONTEXT_VARIABLES, DATA, SETTINGS
 
 logger = getLogger(__name__)
 
@@ -325,5 +325,7 @@ def display_page(_ts, pathname, search):
         """
         dash_app.config.suppress_callback_exceptions = False
         params = chart_url_params(search)
-        df = DATA[get_data_id(pathname)]
-        return charts_layout(df, **params)
+        data_id = get_data_id(pathname)
+        df = DATA[data_id]
+        settings = SETTINGS.get(data_id) or {}
+        return charts_layout(df, settings, **params)

dtale/static/css/dash.css

@@ -472,7 +472,9 @@ div.tab-container > div.tab:last-child {
     border: 1px solid #a7b3b7;
     border-radius: 0 .25rem .25rem 0;
 }
-div.modebar > div.modebar-group:last-child {
-    display: none;  /* hide plotly logo */
+div.modebar > div.modebar-group:last-child, /* hide plotly logo */
+div.modebar > div.modebar-group:first-child /* hide plotly "export to png" */
+{
+    display: none;
 }
 

dtale/utils.py

@@ -772,7 +772,7 @@ def run_query(df, query, context_vars):
     :param df: input dataframe
     :type df: :class:`pandas:pandas.DataFrame`
     :param query: query string
-    :type query: string
+    :type query: str
     :param context_vars: dictionary of user-defined variables which can be referenced by name in query strings
     :type context_vars: dict
     :return: filtered dataframe
@@ -804,3 +804,9 @@ def run_query(df, query, context_vars):
     if not len(df):
         raise Exception('query "{}" found no data, please alter'.format(query))
     return df
+
+
+class DuplicateDataError(Exception):
+    def __init__(self, data_id):
+        super(DuplicateDataError, self).__init__("Duplicate Data")
+        self.data_id = data_id