Merge pull request #124 from ricardogsilva/109-define-decades-as-1-10…

…-and-not-0-9 Modify decade grouping
geobeyond · Jun 6, 2024 · 89bfbf4 · 89bfbf4
2 parents d25665a + b226189
commit 89bfbf4
Show file tree

Hide file tree

Showing 2 changed files with 31 additions and 33 deletions.
diff --git a/arpav_ppcv/operations.py b/arpav_ppcv/operations.py
@@ -70,13 +70,21 @@ def get_observation_time_series(
     info = {}
 
     if include_decade_data:
-        decade_df = df.groupby((df.index.year // 10) * 10).mean()
-        decade_df = decade_df.drop(columns=[base_name])
+        # group values by climatological decade, which starts at year 1 and ends at year 10
+        decade_grouper = df.groupby(((df.index.year - 1) // 10) * 10)
+
+        mean_column_name = f"{base_name}__DECADE_MEAN"
+        decade_df = decade_grouper.agg(
+            num_values=(unsmoothed_col_name, "size"),
+            **{mean_column_name: (unsmoothed_col_name, "mean")},
+        )
+
+        # discard decades where there are less than 7 years
+        decade_df = decade_df[decade_df.num_values >= 7]
+
+        decade_df = decade_df.drop(columns=["num_values"])
         decade_df["time"] = pd.to_datetime(decade_df.index.astype(str), utc=True)
         decade_df.set_index("time", inplace=True)
-        decade_df = decade_df.rename(
-            columns={unsmoothed_col_name: f"{base_name}__DECADE_MEAN"}
-        )
     else:
         decade_df = None
 

diff --git a/tests/notebooks/observation-time-series.ipynb b/tests/notebooks/observation-time-series.ipynb
@@ -31,12 +31,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 2,
    "id": "233ab640-9ac4-4fe0-b4b3-31e177cb67b1",
    "metadata": {},
    "outputs": [],
    "source": [
-    "df, decade_df, mk_df = operations.get_observation_time_series(\n",
+    "df, decade_df, mk_df, info = operations.get_observation_time_series(\n",
     "    session,\n",
     "    variable,\n",
     "    station,\n",
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "65b0cbc2-58be-4001-9653-bd0386ae2283",
    "metadata": {},
    "outputs": [
@@ -322,7 +322,7 @@
        "2024-01-01 00:00:00+00:00              2.416                          NaN"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -333,7 +333,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 4,
    "id": "574e423c-35f1-4c1f-a1eb-5295c8b187df",
    "metadata": {},
    "outputs": [
@@ -367,40 +367,30 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>1980</th>\n",
-       "      <td>0.845667</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1990</th>\n",
-       "      <td>1.246000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2000</th>\n",
-       "      <td>0.847400</td>\n",
+       "      <th>1990-01-01 00:00:00+00:00</th>\n",
+       "      <td>1.0870</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2010</th>\n",
-       "      <td>1.280200</td>\n",
+       "      <th>2000-01-01 00:00:00+00:00</th>\n",
+       "      <td>0.8325</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2020</th>\n",
-       "      <td>1.941400</td>\n",
+       "      <th>2010-01-01 00:00:00+00:00</th>\n",
+       "      <td>1.6243</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "      TDd__DECADE_MEAN\n",
-       "time                  \n",
-       "1980          0.845667\n",
-       "1990          1.246000\n",
-       "2000          0.847400\n",
-       "2010          1.280200\n",
-       "2020          1.941400"
+       "                           TDd__DECADE_MEAN\n",
+       "time                                       \n",
+       "1990-01-01 00:00:00+00:00            1.0870\n",
+       "2000-01-01 00:00:00+00:00            0.8325\n",
+       "2010-01-01 00:00:00+00:00            1.6243"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -621,7 +611,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.8"
+   "version": "3.10.14"
   }
  },
  "nbformat": 4,