local vscode
This commit is contained in:
@@ -187,7 +187,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 91,
|
||||
"id": "4cc14bd0",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -201,46 +201,21 @@
|
||||
"| GB| NULL| NULL| false| 31.94.22.158| Last Day Of Summer| Summer Walker| Girls Need Love| 80505| false| 1680818230| ios|unexpected-exit-w...| trackdone| true| false| NULL|spotify:track:644...|2023-04-06T21:58:31Z| unknown| csm3-us|\n",
|
||||
"+------------+------------+-----------------+--------------+-----------------+--------------------------------+---------------------------------+--------------------------+---------+-------+-----------------+--------+--------------------+------------+-------+-------+-------------------+--------------------+--------------------+--------------------+--------+\n",
|
||||
"only showing top 1 row\n",
|
||||
"+-------+--------------------+-----+\n",
|
||||
"|skipped| reason_end|count|\n",
|
||||
"+-------+--------------------+-----+\n",
|
||||
"| false| unknown| 99|\n",
|
||||
"| NULL| unknown| 375|\n",
|
||||
"| false|unexpected-exit-w...| 1243|\n",
|
||||
"| NULL|unexpected-exit-w...| 432|\n",
|
||||
"| false| unexpected-exit| 36|\n",
|
||||
"| NULL| unexpected-exit| 51|\n",
|
||||
"| false| trackerror| 69|\n",
|
||||
"| NULL| trackerror| 33|\n",
|
||||
"| false| trackdone|36102|\n",
|
||||
"| NULL| trackdone|24077|\n",
|
||||
"| false| remote| 121|\n",
|
||||
"| NULL| remote| 859|\n",
|
||||
"| false| logout| 491|\n",
|
||||
"| NULL| logout| 745|\n",
|
||||
"| true| fwdbtn|16571|\n",
|
||||
"| NULL| fwdbtn|11445|\n",
|
||||
"| true| endplay| 2943|\n",
|
||||
"| NULL| endplay| 1447|\n",
|
||||
"| true| backbtn| 650|\n",
|
||||
"| NULL| backbtn| 402|\n",
|
||||
"+-------+--------------------+-----+\n",
|
||||
"only showing top 20 rows\n",
|
||||
"+----------------------------+-----+\n",
|
||||
"|reason_end |count|\n",
|
||||
"+----------------------------+-----+\n",
|
||||
"|trackdone |60179|\n",
|
||||
"|fwdbtn |28016|\n",
|
||||
"|NULL |4435 |\n",
|
||||
"|endplay |4390 |\n",
|
||||
"|unexpected-exit-while-paused|1675 |\n",
|
||||
"|logout |1236 |\n",
|
||||
"|backbtn |1052 |\n",
|
||||
"|remote |980 |\n",
|
||||
"|unknown |474 |\n",
|
||||
"|trackerror |102 |\n",
|
||||
"|unexpected-exit |87 |\n",
|
||||
"+----------------------------+-----+\n",
|
||||
"+----------------------------+--------------+\n",
|
||||
"|reason_end |skipped_values|\n",
|
||||
"+----------------------------+--------------+\n",
|
||||
"|NULL |[] |\n",
|
||||
"|backbtn |[true] |\n",
|
||||
"|endplay |[true] |\n",
|
||||
"|fwdbtn |[true] |\n",
|
||||
"|logout |[false] |\n",
|
||||
"|remote |[false] |\n",
|
||||
"|trackdone |[false] |\n",
|
||||
"|trackerror |[false] |\n",
|
||||
"|unexpected-exit |[false] |\n",
|
||||
"|unexpected-exit-while-paused|[false] |\n",
|
||||
"|unknown |[false] |\n",
|
||||
"+----------------------------+--------------+\n",
|
||||
"\n",
|
||||
" Raw DF Rows: 105477\n",
|
||||
" Transformed DF Rows: 102626\n",
|
||||
@@ -260,10 +235,14 @@
|
||||
" transformed_df = clean_track_df(raw_df)\n",
|
||||
" #load_data(transformed_df, table_name)\n",
|
||||
" # transformed_df.show(5)\n",
|
||||
" skip_reason_df = transformed_df.groupBy(\"skipped\", \"reason_end\").count().orderBy(F.desc(\"reason_end\")).show()\n",
|
||||
" # skip_reason_df = transformed_df.groupBy(\"skipped\", \"reason_end\").count().orderBy(F.desc(\"reason_end\")).show()\n",
|
||||
" # reason_df = transformed_df.groupBy(\"reason_end\").orderBy(F.desc(\"count\")).show(5)\n",
|
||||
" # skip_df = transformed_df.groupBy(\"skipped\").count().orderBy(F.desc(\"count\")).show(5)\n",
|
||||
" skip_join_bool = transformed_df.select(\"reason_end\", \"was_skipped\").distinct().orderBy(\"reason_end\").show(truncate=False))\n",
|
||||
" # skip_join_bool = transformed_df.select(\"reason_end\", \"skipped\").distinct().orderBy(\"reason_end\").show(100)\n",
|
||||
" skip_reason_bool = (transformed_df.groupBy(\"reason_end\")\n",
|
||||
" .agg(F.collect_set(\"skipped\").alias(\"skipped_values\"))\n",
|
||||
" .orderBy(\"reason_end\")\n",
|
||||
" .show(truncate=False))\n",
|
||||
" #join(transformed_df.F.col(\"reason_end\"))\n",
|
||||
"\n",
|
||||
" # missing_boolean = set(rename_map) - set(df.columns)\n",
|
||||
|
||||
Reference in New Issue
Block a user