Several CA fixes

activity_browser/bwutils/multilca.py

@@ -1,4 +1,5 @@
 from collections import OrderedDict
+from copy import deepcopy
 from typing import Iterable, Optional, Union
 from logging import getLogger
 
@@ -433,15 +434,30 @@ def _build_dict(
         """
         topcontribution_dict = dict()
         for fu_or_method, col in FU_M_index.items():
+
+            contribution_col = contributions[col, :]
+            total = contribution_col.sum()
+
             top_contribution = ca.sort_array(
-                contributions[col, :], limit=limit, limit_type=limit_type
+                contribution_col, limit=limit, limit_type=limit_type, total=total
+            )
+
+            # split and calculate remaining rest sections for positive and negative part
+            pos_rest = (
+                np.sum(contribution_col[contribution_col > 0])
+                - np.sum(top_contribution[top_contribution[:, 0] > 0][:, 0])
+            )
+            neg_rest = (
+                    np.sum(contribution_col[contribution_col < 0])
+                    - np.sum(top_contribution[top_contribution[:, 0] < 0][:, 0])
             )
+
             cont_per = OrderedDict()
             cont_per.update(
                 {
-                    ("Total", ""): contributions[col, :].sum(),
-                    ("Rest", ""): contributions[col, :].sum()
-                    - top_contribution[:, 0].sum(),
+                    ("Total", ""): total,
+                    ("Rest (+)", ""): pos_rest,
+                    ("Rest (-)", ""): neg_rest,
                 }
             )
             for value, index in top_contribution:
@@ -544,12 +560,12 @@ def join_df_with_metadata(
 
         if special_keys:
             # replace index keys with labels
-            try:  # first put Total and Rest to the first two positions in the dataframe
+            try:  # first put Total, Rest (+) and Rest (-) to the first three positions in the dataframe
                 complete_index = special_keys + keys
                 joined = joined.reindex(complete_index, axis="index", fill_value=0.0)
             except:
                 log.error(
-                    "Could not put Total and Rest on positions 0 and 1 in the dataframe."
+                    "Could not put 'Total', 'Rest (+)' and 'Rest (-)' on positions 0, 1 and 2 in the dataframe."
                 )
         joined.index = cls.get_labels(joined.index, fields=x_fields)
         return joined
@@ -583,7 +599,7 @@ def get_labelled_contribution_dict(
         # If the cont_dict has tuples for keys, coerce df.columns into MultiIndex
         if all(isinstance(k, tuple) for k in cont_dict.keys()):
             df.columns = pd.MultiIndex.from_tuples(df.columns)
-        special_keys = [("Total", ""), ("Rest", "")]
+        special_keys = [("Total", ""), ("Rest (+)", ""), ("Rest (-)", "")]
 
         # replace all 0 values with NaN and drop all rows with only NaNs
         # EXCEPT for the special keys
@@ -596,6 +612,17 @@ def get_labelled_contribution_dict(
         )
         df = df.loc[index]
 
+        # sort on absolute mean of a row
+        df_bot = deepcopy(df.iloc[3:, :])
+
+        func = lambda row: np.nanmean(np.abs(row))
+
+        df_bot["_sort_me_"] = (df_bot.select_dtypes(include=np.number)).apply(func, axis=1)
+        df_bot.sort_values(by="_sort_me_", ascending=False, inplace=True)
+        del df_bot["_sort_me_"]
+
+        df = pd.concat([df.iloc[:3, :], df_bot], axis=0)
+
         if not mask:
             joined = self.join_df_with_metadata(
                 df, x_fields=x_fields, y_fields=y_fields, special_keys=special_keys
@@ -617,7 +644,7 @@ def adjust_table_unit(df: pd.DataFrame, method: Optional[tuple]) -> pd.DataFrame
         """Given a dataframe, adjust the unit of the table to either match the given method, or not exist."""
         if "unit" not in df.columns:
             return df
-        keys = df.index[~df["index"].isin({"Total", "Rest"})]
+        keys = df.index[~df["index"].isin({"Total", "Rest (+)", "Rest (-)"})]
         unit = bd.Method(method).metadata.get("unit") if method else "unit"
         df.loc[keys, "unit"] = unit
         return df

activity_browser/docs/wiki/LCA-Results.md

@@ -69,7 +69,7 @@ we call the _from_ part of the contributions (the EFs or activities above) _enti
 There are several ways Activity Browser manipulates your results by default.
 - The results are **sorted** so that the row with the largest (absolute) average values are shown first.
 - A `cut-off` of 5% is applied, this only shows results that contribute at least 5% to the total result, 
-  all other entities are grouped into a `Rest` group.
+  all other entities are grouped into a `Rest (+)` or `Rest (-)` groups.
 - The contributions are _normalized_ to the impact of that reference flow, meaning they are show as a percentage, 
   counting up to 100% for every item you compare.
 
@@ -84,7 +84,8 @@ The `Relative` mode shows contributions _from_ entities of _x_% or higher.
 The `Top #` mode shows contributions from the _x_ entities that contribute the most (as absolute).
 You can adjust the `Cut-off level` to change how many results you see.
 
-All results that don't make the cut-off will be grouped into the `Rest` group.
+All results that don't make the cut-off will be grouped into the `Rest (+)` and `Rest (-)` groups.
+The Rest groups are only present when there are positive or negative numbers remaining for the respective rest groups. 
 
 #### Compare
 The `Compare` menu allows you to compare different dimensions of results.
@@ -107,7 +108,28 @@ You can disable one of them if you want to focus on one of them.
 
 #### Relative and Absolute
 Finally, you can choose between `Relative` and `Absolute` results.
-The `Relative` results will sum to 100%, the `Absolute` results will sum to the impact score.
+The `Relative` results will sum to 100% (the total score), the `Absolute` results will sum to the impact score.
+
+### Positive and negative numbers in contribution results
+It can happen in LCA that you get both positive and negative numbers in your contribution results.
+Some of these reasons could be negative characterization factors, flows with negative numbers or using substitution flows.
+
+When there are both positive and negative numbers in the result, Activity Browser will show a marker to indicate 
+where the total score is, and show positive and negative contributions to the impact separately.
+
+Below is a simple example (with unrealistic values) to demonstrate this:
+
+![CA example with positive and negative results](./assets/ca_positive_negative_example.png)
+
+Other softwares (e.g. [Brightway2-Analyzer](https://github.com/brightway-lca/brightway2-analyzer)) 
+may use a different 'total', meaning the contributions may look different.
+For example, Brightway2-Analyzer uses the total of absolute values 
+(so the range of numbers from the lowest negative number to the highest positive number) as 100% of the score.
+
+> [!IMPORTANT]
+> Due to Activity Browser using 100% as the 'total' when you sum all positive contributions, 
+> positive results will sum to over 100% when there are also negative numbers, which will sum together to 100%.
+> Even single contributions may be over 100%. 
 
 ## Sankey
 The `Sankey` tab shows results from [graph traversal](https://docs.brightway.dev/projects/graphtools/en/latest/index.html).

activity_browser/ui/figures.py

@@ -182,14 +182,17 @@ def __init__(self):
         self.plot_name = "Contributions"
 
     def plot(self, df: pd.DataFrame, unit: str = None):
-        """Plot a horizontal bar chart of the process contributions."""
+        """Plot a horizontal stacked bar chart of contributions,
+        add 'total' marker if both positive and negative results are present."""
         dfp = df.copy()
         dfp.index = dfp["index"]
         dfp.drop(
             dfp.select_dtypes(["object"]), axis=1, inplace=True
         )  # get rid of all non-numeric columns (metadata)
         if "Total" in dfp.index:
             dfp.drop("Total", inplace=True)
+        # drop rows if all values are 0
+        dfp = dfp.loc[~(dfp == 0).all(axis=1)]
 
         self.ax.clear()
         canvas_width_inches, canvas_height_inches = self.get_canvas_size_in_inches()
@@ -204,9 +207,18 @@ def plot(self, df: pd.DataFrame, unit: str = None):
         dfp.index = dfp.index.str.strip("_ \n\t")
         dfp.columns = dfp.columns.str.strip("_ \n\t")
 
+        # set colormap to use
+        items = dfp.shape[0]  # how many contribution items
+        # skip grey and black at start/end of cmap
+        cmap = plt.cm.nipy_spectral_r(np.linspace(0, 1, items + 2))[1:-1]
+        colors = {item: color for item, color in zip(dfp.index, cmap)}
+        # overwrite rest values to grey
+        colors["Rest (+)"] = [0.8, 0.8, 0.8, 1.]
+        colors["Rest (-)"] = [0.8, 0.8, 0.8, 1.]
+
         dfp.T.plot.barh(
             stacked=True,
-            cmap=plt.cm.nipy_spectral_r,
+            color=colors,
             ax=self.ax,
             legend=False if dfp.shape[0] >= self.MAX_LEGEND else True,
         )
@@ -225,6 +237,16 @@ def plot(self, df: pd.DataFrame, unit: str = None):
         self.ax.grid(which="major", axis="x", color="grey", linestyle="dashed")
         self.ax.set_axisbelow(True)  # puts gridlines behind bars
 
+        # total marker when both negative and positive results are present in a column
+        marker_size = max(min(150 / dfp.shape[1], 35), 10)  # set marker size dyanmic between 10 - 35
+        for i, col in enumerate(dfp):
+            total = np.sum(dfp[col])
+            abs_total = np.sum(np.abs(dfp[col]))
+            if abs(total) != abs_total:
+                self.ax.plot(total, i,
+                             markersize=marker_size, marker="d", fillstyle="left",
+                             markerfacecolor="black", markerfacecoloralt="grey", markeredgecolor="white")
+
         # TODO review: remove or enable
 
         # refresh canvas

activity_browser/ui/tables/models/lca_results.py

@@ -28,8 +28,6 @@ def sync(self, df):
 
 class ContributionModel(PandasModel):
     def sync(self, df):
-        self._dataframe = df.replace(np.nan, "", regex=True)
-        # drop the 'rest' row if empty
-        if self._dataframe.select_dtypes(include=np.number).iloc[1, :].sum() == 0:
-            self._dataframe.drop(labels=1, inplace=True)
+        # drop any rows where all numbers are 0
+        self._dataframe = df.loc[~(df.select_dtypes(include=np.number) == 0).all(axis=1)]
         self.updated.emit()