Merge pull request #69 from unicef-drp/average_line

Average line

dash_service/pages/transmonee.py

@@ -187,6 +187,10 @@
 
 years = list(range(2000, 2025))
 
+# some indexes have been listed as ratios in SDG database so we need to specify not to round these indicators
+codes_3_decimals = ['HVA_EPI_INF_RT_0-14', 'EDU_SE_TOT_GPI_L2_MAT', 'EDU_SE_TOT_GPI_L2_REA', 'EDU_SE_AGP_CPRA_L3']
+codes_1_decimal = ['DM_FRATE_COMP', 'PV_GINI_COEF']
+
 # a key:value dictionary of countries where the 'key' is the country name as displayed in the selection
 # tree whereas the 'value' is the country name as returned by the sdmx list: https://sdmx.data.unicef.org/ws/public/sdmxapi/rest/codelist/UNICEF/CL_COUNTRY/1.0
 countries_iso3_dict = {
@@ -1060,10 +1064,6 @@ def get_data(
     data["OBS_FOOTNOTE"] = data.OBS_FOOTNOTE.str.wrap(70).str.replace("\n", "<br>")
     data["DATA_SOURCE"] = data.DATA_SOURCE.str.wrap(70).str.replace("\n", "<br>")
 
-    # some indexes have been listed as ratios in SDG database so we need to specify not to round these indicators
-    codes_3_decimals = ['HVA_EPI_INF_RT_0-14', 'EDU_SE_TOT_GPI_L2_MAT', 'EDU_SE_TOT_GPI_L2_REA', 'EDU_SE_AGP_CPRA_L3']
-    codes_1_decimal = ['DM_FRATE_TOT', 'PV_GINI_COEF']
-
     if "IDX" in data.UNIT_MEASURE.values or any(code in data.CODE.values for code in codes_3_decimals):
         data.OBS_VALUE = data.OBS_VALUE.round(3)
     elif any(code in data.CODE.values for code in codes_1_decimal):
@@ -1515,7 +1515,7 @@ def get_base_layout(**kwargs):
                                     ),
                                 ],
                                 style={"display":"flex", "justify-content":"center"},
-                                lg=10, md=10, sm=12, xs=12
+                                lg=12, md=12, sm=12, xs=12
                             ),
                             dbc.Col(width=1),
                         ],
@@ -2631,6 +2631,7 @@ def fig_options(indicator):
     # Use base_indicator for the rest of the function
     indicator_config = indicators_config.get(indicator, {})
 
+
     # Check if the indicator has is string type and give only bar and map as options
     if indicator_config and nominal_data(indicator_config):
         area_types = [
@@ -2644,7 +2645,10 @@ def fig_options(indicator):
             {"label": "Trend data", "value": "line"},
             {"label": "Map of data", "value": "map"},
         ]
-        default_graph = "bar"
+        if indicator == 'DM_POP_NETM':
+            default_graph = "map"
+        else:
+            default_graph = "bar"
 
     return area_types, default_graph
 
@@ -2869,6 +2873,8 @@ def aio_area_figure(
             "",
         )
 
+    data['type'] = 'country'
+
     # indicator card
     card_key = indicator
 
@@ -2907,8 +2913,8 @@ def aio_area_figure(
     df_indicator_sources = df_sources[df_sources["Code"] == base_indicator]
     unique_indicator_sources = df_indicator_sources["Source_Full"].unique()
 
-    if data["CODE"].isin(["DM_CHLD_POP", "DM_CHLD_POP_PT", "DM_ADOL_POP", "DM_UFIVE_POP"]).any():
-        source = " Multiple Sources"
+    if data["CODE"].isin(["DM_CHLD_POP", "DM_CHLD_POP_PT", "DM_FRATE_COMP","DM_ADOL_POP", "DM_UFIVE_POP"]).any():
+        source = "Multiple Sources"
     elif len(unique_indicator_sources) > 0:
         source = "; ".join(list(unique_indicator_sources))
     else:
@@ -2917,7 +2923,7 @@ def aio_area_figure(
     source_link = (
         df_indicator_sources["Source_Link"].unique()[0]
         if len(unique_indicator_sources) > 0
-        and not data["CODE"].isin(["DM_CHLD_POP", "DM_CHLD_POP_PT", "DM_ADOL_POP", "DM_UFIVE_POP"]).any()
+        and not data["CODE"].isin(["DM_CHLD_POP", "DM_CHLD_POP_PT", "DM_FRATE_COMP", "DM_ADOL_POP", "DM_UFIVE_POP"]).any()
         else "https://ec.europa.eu/eurostat/cache/metadata/en/demo_pop_esms.htm"
     )
 
@@ -3123,9 +3129,25 @@ def aio_area_figure(
             options["text_auto"] = False
         if (data['OBS_VALUE'] == 0).any():
             graph_info =  graph_info + "Zero values not showing on graph; see 'Countries with data' for more information."
+
+    if fig_type == "bar" and not dimension and "PS" not in data.UNIT_MEASURE.values:
+        # Calculate the average of the 'Value' column
+        average_value = data["OBS_VALUE"].mean()
+
+        if "IDX" in data.UNIT_MEASURE.values or any(code in data.CODE.values for code in codes_3_decimals):
+            average_value = round(average_value, 3)
+        #elif any(code in data.CODE.values for code in codes_1_decimal):
+            #average_value = round(average_value, 1)
+        else:
+            average_value = round(average_value, 1)
+
+            # Convert to int if there are no decimals
+        #if average_value == round(average_value):
+         #   average_value = int(average_value)
 
     # removing zero values from bar chart as they cause a bug where countries without data display on chart
     fig_data = data[data['OBS_VALUE'] != 0] if fig_type == "bar" else data
+    print(fig_data)
 
     if fig_type == "count_bar":
         # change to fig type to generate px.bar
@@ -3137,18 +3159,28 @@ def aio_area_figure(
     fig.update_layout(yaxis_title=y_axis_title)
     # remove x-axis title but keep space below
     fig.update_layout(xaxis_title="")
-    if fig_type == "bar" and not dimension and "YES_NO" not in data.UNIT_MEASURE.values and base_indicator != 'PP_SG_NHR_STATUS':
+    if fig_type == "bar" and not dimension and "YES_NO" not in fig_data.UNIT_MEASURE.values and base_indicator != 'PP_SG_NHR_STATUS':
         fig.update_traces(marker_color=domain_colour)
         fig.update_layout(showlegend=False)
+        if "PS" not in fig_data.UNIT_MEASURE.values:
+            annotation_text = f"Average: {average_value}% " if any(unit in fig_data.UNIT_MEASURE.values for unit in ["PCNT", "GOV_EXP_EDU"]) else f"Average: {average_value}"
+            fig.add_hline(
+                y=average_value, 
+                line_color="#1cabe2", 
+                line_width=2, 
+                line_dash="dot",
+                annotation_text=annotation_text, 
+                annotation_position="top right"
+            )
     if fig_type == "line":
         fig.update_traces(**traces)
         # adding invisible line at zero to make sure the y-axis starts at zero
         fig.add_hline(y=-0.3, line_color="rgba(0,0,0,0)")
 
     fig.update_traces(hovertemplate=hovertext)
 
-    if fig_type == "bar" and "YES_NO" in data.UNIT_MEASURE.values:
-        dfs = data.groupby("Status").count()
+    if fig_type == "bar" and "YES_NO" in fig_data.UNIT_MEASURE.values:
+        dfs = fig_data.groupby("Status").count()
         fig.add_trace(
             go.Scatter(
                 x=dfs.index,

dash_service/static/crm_framework_indicators.json

@@ -265,7 +265,7 @@
                 },
                 {
                     "Indicator Name": "Total fertility rate",
-                    "Code": "DM_FRATE_TOT"
+                    "Code": "DM_FRATE_COMP"
                 },
                 {
                     "Indicator Name": "Number of births",

dash_service/static/indicator_buttons.json

@@ -8,7 +8,7 @@
     "DM_CHLD_YOUNG_COMP_POP": NaN,
     "DM_CHLD_YOUNG_POP": NaN,
     "DM_CHLD_POP_PT": "Children as a share of the total population",
-    "DM_FRATE_TOT": "Total fertility rate",
+    "DM_FRATE_COMP": "Total fertility rate",
     "DM_BRTS": "Number of births",
     "DM_SP_POP_BRTH_MF": NaN,
     "DM_LIFE_EXP": NaN,

dash_service/static/indicator_definitions.json

@@ -8,7 +8,7 @@
     "DM_CHLD_YOUNG_COMP_POP": "Compiled child, young people and total population, 0-17 and 18-24 years (1989-present)",
     "DM_CHLD_YOUNG_POP": "Child and young people population, 0-17 and 18-24 years, at the beginning of the year",
     "DM_CHLD_POP_PT": "Children as a percentage of the total population compiled from multiple sources. Figures for male and female represent the share of the male and female population respectively. Data comes from Eurostat, UN DESA or in some cases it has been directly submitted by the NSO (for Belarus, Georgia and Tajikistan).",
-    "DM_FRATE_TOT": "Average number of live births a hypothetical cohort of women (aged 15-49 years) would have at the end of their reproductive period if they were subject during their whole lives to the fertility rates of a given period and if they were not subject to mortality",
+    "DM_FRATE_COMP": "Total fertility rate is computed by adding the age specific fertility rates for women in a given year. It can be interpreted as the mean number of children that would be born alive to a woman during her lifetime if she were to pass through her childbearing years conforming to the fertility rates by age of a given year, and surviving. Data is compiled from multiple sources (Eurostat & UN DESA).",
     "DM_BRTS": "Number of births (in thousands)",
     "DM_SP_POP_BRTH_MF": "Sex ratio at birth refers to male births per female births. The data are for 5 year averages.",
     "DM_LIFE_EXP": "Average number of years newborn children would live if subject to the mortality risks prevailing for the cross section of population at the time of their birth",

dash_service/static/page_config.py

@@ -149,7 +149,7 @@
                         "yaxis": 'Number of births',
                         'button_name': 'Number of births'},
                         {'name': 'Total fertility rate',
-                        'indicator': 'DM_FRATE_TOT',
+                        'indicator': 'DM_FRATE_COMP',
                         'suffix': min_max_card_suffix,
                         'min_max': True,
                         "yaxis": 'Total fertility rate',
@@ -164,7 +164,7 @@
                         'indicators': ['DM_CHLD_POP',
                         'DM_CHLD_POP_PT',
                         'DM_BRTS',
-                        'DM_FRATE_TOT',
+                        'DM_FRATE_COMP',
                         'DM_POP_NETM'],
                         'default_graph': 'bar',
                         'default': 'DM_CHLD_POP'}},

dash_service/static/structured_data.json

@@ -223,7 +223,7 @@
                 "Indicator Name": "Percentage of children as a share of the total population"
             },
             {
-                "Code": "DM_FRATE_TOT",
+                "Code": "DM_FRATE_COMP",
                 "Indicator Name": "Total fertility rate (average live births per woman aged 15-49)"
             },
             {

dash_service/tmp/transmonee - Copia.py

@@ -727,7 +727,7 @@ def get_data(
 
     if "IDX" in data.UNIT_MEASURE.values or "HVA_EPI_INF_RT_0-14" in data.CODE.values:
         data.OBS_VALUE = data.OBS_VALUE.round(3)
-    elif "DM_FRATE_TOT" in data.CODE.values:
+    elif "DM_FRATE_COMP" in data.CODE.values:
         data.OBS_VALUE = data.OBS_VALUE.round(1)
     else:
         data.OBS_VALUE = data.OBS_VALUE.round(1)