Adding Long Descriptions (#244)

* Responding to issue #67, Added color for bar charts.

* Minor: Updated spacing

* Updated BarChar.py to disable legends for basic bar plots

* changing colors for bar charts

* fixing merge error

* started adding in long descriptions

* fixed style

* Changed naming to conform w/ PEP8

* rename

* rename

* Update correlation.py

* Update univariate.py

* made required fields dynamic

* added links

* added to description length

lux/action/column_group.py

@@ -26,6 +26,11 @@ def column_group(ldf):
     recommendation = {
         "action": "Column Groups",
         "description": "Shows charts of possible visualizations with respect to the column-wise index.",
+        "long_description": 'A column index can be thought of as an extra column that indicates the values that the user is interested in. \
+            Lux focuses on visualizing named dataframe indices, i.e., indices with a non-null name property, as a proxy of the attribute \
+                that the user is interested in or have operated on (e.g., group-by attribute). In particular, dataframes with named indices \
+                    are often pre-aggregated, so Lux visualizes exactly the values that the dataframe portrays.  \
+                        <a href="https://lux-api.readthedocs.io/en/latest/source/advanced/indexgroup.html" target="_blank">More details</a>',
     }
     collection = []
     ldf_flat = ldf

lux/action/correlation.py

@@ -48,9 +48,17 @@ def correlation(ldf: LuxDataFrame, ignore_transpose: bool = True):
     ]
     intent.extend(filter_specs)
     vlist = VisList(intent, ldf)
+    examples = ""
+    if len(vlist) > 1:
+        measures = vlist[0].get_attr_by_data_model("measure")
+        if len(measures) >= 2:
+            examples = f" (e.g., {measures[0].attribute}, {measures[1].attribute})"
     recommendation = {
         "action": "Correlation",
         "description": "Show relationships between two <p class='highlight-descriptor'>quantitative</p> attributes.",
+        "long_description": f"Correlation searches through all pairwise relationship between two quantitative attributes\
+            {examples}. The visualizations are ranked from most to least linearly correlated based on \
+                their Pearson’s correlation score.",
     }
     ignore_rec_flag = False
     # Doesn't make sense to compute correlation if less than 4 data values

lux/action/custom.py

@@ -36,6 +36,7 @@ def custom(ldf):
     recommendation = {
         "action": "Current Vis",
         "description": "Shows the list of visualizations generated based on user specified intent",
+        "long_description": "Shows the list of visualizations generated based on user specified intent",
     }
 
     recommendation["collection"] = ldf.current_vis

lux/action/enhance.py

@@ -43,11 +43,13 @@ def enhance(ldf):
         recommendation = {
             "action": "Enhance",
             "description": f"Augmenting current {intended_attrs} intent with additional attribute.",
+            "long_description": f"Enhance adds an additional attribute displaying how {intended_attrs} changes with respect to other attributes. Visualizations are ranked based on interestingness. The top 15 visualizations are displayed.",
         }
     elif len(attr_specs) == 2:
         recommendation = {
             "action": "Enhance",
             "description": f"Further breaking down current {intended_attrs} intent by additional attribute.",
+            "long_description": f"Enhance adds an additional attribute as the color to break down the {intended_attrs} distribution",
         }
     # if there are too many column attributes, return don't generate Enhance recommendations
     elif len(attr_specs) > 2:

lux/action/filter.py

@@ -49,6 +49,7 @@ def add_filter(ldf):
             recommendation = {
                 "action": "Filter",
                 "description": f"Changing the <p class='highlight-intent'>{fltr.attribute}</p> filter to an alternative value.",
+                "long_description": f"Swap out the filter value for {fltr.attribute} to other possible values, while keeping all else the same. Visualizations are ranked based on interestingness",
             }
             unique_values = ldf.unique_values[fltr.attribute]
             filter_values.append(fltr.value)
@@ -64,6 +65,7 @@ def add_filter(ldf):
             recommendation = {
                 "action": "Filter",
                 "description": f"Changing the <p class='highlight-intent'>{fltr.attribute}</p> filter to an alternative inequality operation.",
+                "long_description": f"Changing the <p class='highlight-intent'>{fltr.attribute}</p> filter to an alternative inequality operation.",
             }
 
             def get_complementary_ops(fltr_op):
@@ -99,6 +101,7 @@ def get_complementary_ops(fltr_op):
         recommendation = {
             "action": "Filter",
             "description": f"Applying filters to the <p class='highlight-intent'>{intended_attrs}</p> intent.",
+            "long_description": f"Adding any filter while keeping the attributes on the x and y axes fixed. Visualizations are ranked based on interestingness",
         }
         categorical_vars = []
         for col in list(ldf.columns):
@@ -122,6 +125,7 @@ def get_complementary_ops(fltr_op):
         recommendation = {
             "action": "Similarity",
             "description": "Show other charts that are visually similar to the Current vis.",
+            "long_description": "Show other charts that are visually similar to the Current vis.",
         }
         last = get_filter_specs(ldf.intent)[-1]
         output = ldf.intent.copy()[0:-1]

lux/action/generalize.py

@@ -48,6 +48,7 @@ def generalize(ldf):
     recommendation = {
         "action": "Generalize",
         "description": f"Remove an attribute or filter from {intended_attrs}.",
+        "long_description": f"Remove one aspect of the Current Vis. We can either remove an attribute or filter from {intended_attrs}.",
     }
     # to observe a more general trend
     # if we do no have enough column attributes or too many, return no vis.

lux/action/row_group.py

@@ -26,6 +26,11 @@ def row_group(ldf):
     recommendation = {
         "action": "Row Groups",
         "description": "Shows charts of possible visualizations with respect to the row-wise index.",
+        "long_description": 'A row index can be thought of as an extra row that indicates the values that the user is interested in. \
+            Lux focuses on visualizing named dataframe indices, i.e., indices with a non-null name property, as a proxy of the attribute \
+                that the user is interested in or have operated on (e.g., group-by attribute). In particular, dataframes with named indices \
+                    are often pre-aggregated, so Lux visualizes exactly the values that the dataframe portrays. \
+                        <a href="https://lux-api.readthedocs.io/en/latest/source/advanced/indexgroup.html" target="_blank">More details</a>',
     }
     collection = []
 

lux/action/univariate.py

@@ -52,26 +52,40 @@ def univariate(ldf, *args):
         ]
         intent = [lux.Clause(possible_attributes)]
         intent.extend(filter_specs)
+        examples = ""
+        if len(possible_attributes) >= 1:
+            examples = f" (e.g., {possible_attributes[0]})"
         recommendation = {
             "action": "Distribution",
             "description": "Show univariate histograms of <p class='highlight-descriptor'>quantitative</p>  attributes.",
+            "long_description": f"Distribution displays univariate histogram distributions of all quantitative attributes{examples}. Visualizations are ranked from most to least skewed.",
         }
         # Doesn't make sense to generate a histogram if there is less than 5 datapoints (pre-aggregated)
         if len(ldf) < 5:
             ignore_rec_flag = True
     elif data_type_constraint == "nominal":
+        possible_attributes = [
+            c
+            for c in ldf.columns
+            if ldf.data_type[c] == "nominal" and ldf.cardinality[c] > 5 and c != "Number of Records"
+        ]
+        examples = ""
+        if len(possible_attributes) >= 1:
+            examples = f" (e.g., {possible_attributes[0]})"
         intent = [lux.Clause("?", data_type="nominal")]
         intent.extend(filter_specs)
         recommendation = {
             "action": "Occurrence",
             "description": "Show frequency of occurrence for <p class='highlight-descriptor'>categorical</p> attributes.",
+            "long_description": f"Occurence displays bar charts of counts for all categorical attributes{examples}. Visualizations are ranked from most to least uneven across the bars. ",
         }
     elif data_type_constraint == "temporal":
         intent = [lux.Clause("?", data_type="temporal")]
         intent.extend(filter_specs)
         recommendation = {
             "action": "Temporal",
             "description": "Show trends over <p class='highlight-descriptor'>time-related</p> attributes.",
+            "long_description": "Temporal displays line charts for all attributes related to datetimes in the dataframe.",
         }
         # Doesn't make sense to generate a line chart if there is less than 3 datapoints (pre-aggregated)
         if len(ldf) < 3: