diff --git a/notebooks/03-overlap.ipynb b/notebooks/03-overlap.ipynb index 1fa3496..a1a13f6 100644 --- a/notebooks/03-overlap.ipynb +++ b/notebooks/03-overlap.ipynb @@ -2791,7 +2791,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 43, "metadata": {}, "outputs": [ { @@ -2849,19 +2849,20 @@ "sum 58 58 58 58 58" ] }, - "execution_count": 14, + "execution_count": 43, "metadata": {}, "output_type": "execute_result" } ], "source": [ "opendoar_dup = dup[dup.source == 'OpenDOAR'].groupby('dedup_id').count()\n", - "opendoar_dup[opendoar_dup.duplicate_id > 1].aggregate(['count', 'sum'])" + "opendoar_dup = opendoar_dup[opendoar_dup.duplicate_id > 1]\n", + "opendoar_dup.aggregate(['count', 'sum'])" ] }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 44, "metadata": {}, "outputs": [ { @@ -2919,19 +2920,20 @@ "sum 6 6 6 6 6" ] }, - "execution_count": 15, + "execution_count": 44, "metadata": {}, "output_type": "execute_result" } ], "source": [ "re3data_dup = dup[dup.source == 're3data'].groupby('dedup_id').count()\n", - "re3data_dup[re3data_dup.duplicate_id > 1].aggregate(['count', 'sum'])" + "re3data_dup = re3data_dup[re3data_dup.duplicate_id > 1]\n", + "re3data_dup.aggregate(['count', 'sum'])" ] }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 45, "metadata": {}, "outputs": [ { @@ -2989,40 +2991,113 @@ "sum 518 518 518 518 518" ] }, - "execution_count": 16, + "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "roar_dup = dup[dup.source == 'roar'].groupby('dedup_id').count()\n", - "roar_dup[roar_dup.duplicate_id > 1].aggregate(['count', 'sum'])" + "roar_dup = roar_dup[roar_dup.duplicate_id > 1]\n", + "roar_dup.aggregate(['count', 'sum'])" ] }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 46, "metadata": {}, "outputs": [ { "data": { + "text/html": [ + "
\n", + " | duplicate_id | \n", + "original_id | \n", + "name | \n", + "source | \n", + "unique_id | \n", + "
---|---|---|---|---|---|
count | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "
sum | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "