Skip to content

Commit ea4f197

Browse files
gahjellegahjelle
committed
Black reformatting
1 parent 7e1c078 commit ea4f197

File tree

2 files changed

+53
-99
lines changed

2 files changed

+53
-99
lines changed

‎data-analysis/data_analysis_findings.ipynb‎

Lines changed: 45 additions & 89 deletions
Original file line numberDiff line numberDiff line change
@@ -35,8 +35,7 @@
3535
"source": [
3636
"import pandas as pd\n",
3737
"\n",
38-
"james_bond_data = pd.read_csv(\"james_bond_data.csv\").convert_dtypes()\n",
39-
" "
38+
"james_bond_data = pd.read_csv(\"james_bond_data.csv\").convert_dtypes()"
4039
]
4140
},
4241
{
@@ -134,9 +133,7 @@
134133
"source": [
135134
"import pandas as pd\n",
136135
"\n",
137-
"james_bond_data = pd.read_parquet(\n",
138-
" \"james_bond_data.parquet\"\n",
139-
").convert_dtypes()\n",
136+
"james_bond_data = pd.read_parquet(\"james_bond_data.parquet\").convert_dtypes()\n",
140137
"\n",
141138
"james_bond_data"
142139
]
@@ -261,9 +258,7 @@
261258
"outputs": [],
262259
"source": [
263260
"data = james_bond_data.rename(columns=new_column_names).combine_first(\n",
264-
" pd.DataFrame(\n",
265-
" {\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}}\n",
266-
" )\n",
261+
" pd.DataFrame({\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}})\n",
267262
")"
268263
]
269264
},
@@ -292,9 +287,7 @@
292287
"metadata": {},
293288
"outputs": [],
294289
"source": [
295-
"data[\n",
296-
" [\"income_usa\", \"income_world\", \"movie_budget\", \"film_length\"]\n",
297-
"].head()"
290+
"data[[\"income_usa\", \"income_world\", \"movie_budget\", \"film_length\"]].head()"
298291
]
299292
},
300293
{
@@ -307,9 +300,7 @@
307300
"data = (\n",
308301
" james_bond_data.rename(columns=new_column_names)\n",
309302
" .combine_first(\n",
310-
" pd.DataFrame(\n",
311-
" {\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}}\n",
312-
" )\n",
303+
" pd.DataFrame({\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}})\n",
313304
" )\n",
314305
" .assign(\n",
315306
" income_usa=lambda data: (\n",
@@ -331,9 +322,7 @@
331322
"data = (\n",
332323
" james_bond_data.rename(columns=new_column_names)\n",
333324
" .combine_first(\n",
334-
" pd.DataFrame(\n",
335-
" {\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}}\n",
336-
" )\n",
325+
" pd.DataFrame({\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}})\n",
337326
" )\n",
338327
" .assign(\n",
339328
" income_usa=lambda data: (\n",
@@ -373,9 +362,7 @@
373362
"data = (\n",
374363
" james_bond_data.rename(columns=new_column_names)\n",
375364
" .combine_first(\n",
376-
" pd.DataFrame(\n",
377-
" {\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}}\n",
378-
" )\n",
365+
" pd.DataFrame({\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}})\n",
379366
" )\n",
380367
" .assign(\n",
381368
" income_usa=lambda data: (\n",
@@ -394,9 +381,7 @@
394381
" .astype(\"Float64\")\n",
395382
" ),\n",
396383
" film_length=lambda data: (\n",
397-
" data[\"film_length\"]\n",
398-
" .str.removesuffix(\"mins\")\n",
399-
" .astype(\"Int64\")\n",
384+
" data[\"film_length\"].str.removesuffix(\"mins\").astype(\"Int64\")\n",
400385
" ),\n",
401386
" )\n",
402387
")"
@@ -409,9 +394,7 @@
409394
"metadata": {},
410395
"outputs": [],
411396
"source": [
412-
"data[\n",
413-
" [\"income_usa\", \"income_world\", \"movie_budget\", \"film_length\"]\n",
414-
"].info()"
397+
"data[[\"income_usa\", \"income_world\", \"movie_budget\", \"film_length\"]].info()"
415398
]
416399
},
417400
{
@@ -421,9 +404,7 @@
421404
"metadata": {},
422405
"outputs": [],
423406
"source": [
424-
"data[\n",
425-
" [\"income_usa\", \"income_world\", \"movie_budget\", \"film_length\"]\n",
426-
"].head()"
407+
"data[[\"income_usa\", \"income_world\", \"movie_budget\", \"film_length\"]].head()"
427408
]
428409
},
429410
{
@@ -456,9 +437,7 @@
456437
"data = (\n",
457438
" james_bond_data.rename(columns=new_column_names)\n",
458439
" .combine_first(\n",
459-
" pd.DataFrame(\n",
460-
" {\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}}\n",
461-
" )\n",
440+
" pd.DataFrame({\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}})\n",
462441
" )\n",
463442
" .assign(\n",
464443
" income_usa=lambda data: (\n",
@@ -477,16 +456,12 @@
477456
" .astype(\"Float64\")\n",
478457
" ),\n",
479458
" film_length=lambda data: (\n",
480-
" data[\"film_length\"]\n",
481-
" .str.removesuffix(\"mins\")\n",
482-
" .astype(\"Int64\")\n",
459+
" data[\"film_length\"].str.removesuffix(\"mins\").astype(\"Int64\")\n",
483460
" ),\n",
484461
" release_date=lambda data: pd.to_datetime(\n",
485462
" data[\"release_date\"], format=\"%B, %Y\"\n",
486463
" ),\n",
487-
" release_year=lambda data: data[\"release_date\"]\n",
488-
" .dt.year\n",
489-
" .astype(\"Int64\"),\n",
464+
" release_year=lambda data: data[\"release_date\"].dt.year.astype(\"Int64\"),\n",
490465
" )\n",
491466
")"
492467
]
@@ -549,9 +524,7 @@
549524
"data = (\n",
550525
" james_bond_data.rename(columns=new_column_names)\n",
551526
" .combine_first(\n",
552-
" pd.DataFrame(\n",
553-
" {\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}}\n",
554-
" )\n",
527+
" pd.DataFrame({\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}})\n",
555528
" )\n",
556529
" .assign(\n",
557530
" income_usa=lambda data: (\n",
@@ -571,16 +544,12 @@
571544
" * 1000\n",
572545
" ),\n",
573546
" film_length=lambda data: (\n",
574-
" data[\"film_length\"]\n",
575-
" .str.removesuffix(\"mins\")\n",
576-
" .astype(\"Int64\")\n",
547+
" data[\"film_length\"].str.removesuffix(\"mins\").astype(\"Int64\")\n",
577548
" ),\n",
578549
" release_date=lambda data: pd.to_datetime(\n",
579550
" data[\"release_date\"], format=\"%B, %Y\"\n",
580551
" ),\n",
581-
" release_year=lambda data: data[\"release_date\"]\n",
582-
" .dt.year\n",
583-
" .astype(\"Int64\"),\n",
552+
" release_year=lambda data: data[\"release_date\"].dt.year.astype(\"Int64\"),\n",
584553
" )\n",
585554
")"
586555
]
@@ -623,9 +592,7 @@
623592
"data = (\n",
624593
" james_bond_data.rename(columns=new_column_names)\n",
625594
" .combine_first(\n",
626-
" pd.DataFrame(\n",
627-
" {\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}}\n",
628-
" )\n",
595+
" pd.DataFrame({\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}})\n",
629596
" )\n",
630597
" .assign(\n",
631598
" income_usa=lambda data: (\n",
@@ -645,16 +612,12 @@
645612
" * 1000\n",
646613
" ),\n",
647614
" film_length=lambda data: (\n",
648-
" data[\"film_length\"]\n",
649-
" .str.removesuffix(\"mins\")\n",
650-
" .astype(\"Int64\")\n",
615+
" data[\"film_length\"].str.removesuffix(\"mins\").astype(\"Int64\")\n",
651616
" ),\n",
652617
" release_date=lambda data: pd.to_datetime(\n",
653618
" data[\"release_date\"], format=\"%B, %Y\"\n",
654619
" ),\n",
655-
" release_year=lambda data: data[\"release_date\"]\n",
656-
" .dt.year\n",
657-
" .astype(\"Int64\"),\n",
620+
" release_year=lambda data: data[\"release_date\"].dt.year.astype(\"Int64\"),\n",
658621
" bond_actor=lambda data: (\n",
659622
" data[\"bond_actor\"]\n",
660623
" .str.replace(\"Shawn\", \"Sean\")\n",
@@ -694,9 +657,7 @@
694657
"data = (\n",
695658
" james_bond_data.rename(columns=new_column_names)\n",
696659
" .combine_first(\n",
697-
" pd.DataFrame(\n",
698-
" {\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}}\n",
699-
" )\n",
660+
" pd.DataFrame({\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}})\n",
700661
" )\n",
701662
" .assign(\n",
702663
" income_usa=lambda data: (\n",
@@ -716,23 +677,20 @@
716677
" * 1000\n",
717678
" ),\n",
718679
" film_length=lambda data: (\n",
719-
" data[\"film_length\"]\n",
720-
" .str.removesuffix(\"mins\")\n",
721-
" .astype(\"Int64\")\n",
680+
" data[\"film_length\"].str.removesuffix(\"mins\").astype(\"Int64\")\n",
722681
" ),\n",
723682
" release_date=lambda data: pd.to_datetime(\n",
724683
" data[\"release_date\"], format=\"%B, %Y\"\n",
725684
" ),\n",
726-
" release_year=lambda data: data[\"release_date\"]\n",
727-
" .dt.year\n",
728-
" .astype(\"Int64\"),\n",
685+
" release_year=lambda data: data[\"release_date\"].dt.year.astype(\"Int64\"),\n",
729686
" bond_actor=lambda data: (\n",
730687
" data[\"bond_actor\"]\n",
731688
" .str.replace(\"Shawn\", \"Sean\")\n",
732689
" .str.replace(\"MOORE\", \"Moore\")\n",
733690
" ),\n",
734-
" car_manufacturer=lambda data: data[\"car_manufacturer\"]\n",
735-
" .str.replace(\"Astin\", \"Aston\"),\n",
691+
" car_manufacturer=lambda data: data[\"car_manufacturer\"].str.replace(\n",
692+
" \"Astin\", \"Aston\"\n",
693+
" ),\n",
736694
" )\n",
737695
")"
738696
]
@@ -775,9 +733,7 @@
775733
"data = (\n",
776734
" james_bond_data.rename(columns=new_column_names)\n",
777735
" .combine_first(\n",
778-
" pd.DataFrame(\n",
779-
" {\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}}\n",
780-
" )\n",
736+
" pd.DataFrame({\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}})\n",
781737
" )\n",
782738
" .assign(\n",
783739
" income_usa=lambda data: (\n",
@@ -791,7 +747,8 @@
791747
" .astype(\"Float64\")\n",
792748
" ),\n",
793749
" movie_budget=lambda data: (\n",
794-
" data[\"movie_budget\"].replace(\"[$,]\", \"\", regex=True)\n",
750+
" data[\"movie_budget\"]\n",
751+
" .replace(\"[$,]\", \"\", regex=True)\n",
795752
" .astype(\"Float64\")\n",
796753
" * 1000\n",
797754
" ),\n",
@@ -804,18 +761,18 @@
804761
" release_date=lambda data: pd.to_datetime(\n",
805762
" data[\"release_date\"], format=\"%B, %Y\"\n",
806763
" ),\n",
807-
" release_year=lambda data: data[\"release_date\"]\n",
808-
" .dt.year\n",
809-
" .astype(\"Int64\"),\n",
764+
" release_year=lambda data: data[\"release_date\"].dt.year.astype(\"Int64\"),\n",
810765
" bond_actor=lambda data: (\n",
811766
" data[\"bond_actor\"]\n",
812767
" .str.replace(\"Shawn\", \"Sean\")\n",
813768
" .str.replace(\"MOORE\", \"Moore\")\n",
814769
" ),\n",
815-
" car_manufacturer=lambda data: data[\"car_manufacturer\"]\n",
816-
" .str.replace(\"Astin\", \"Aston\"),\n",
817-
" martinis_consumed=lambda data: data[\"martinis_consumed\"]\n",
818-
" .replace(-6, 6),\n",
770+
" car_manufacturer=lambda data: data[\"car_manufacturer\"].str.replace(\n",
771+
" \"Astin\", \"Aston\"\n",
772+
" ),\n",
773+
" martinis_consumed=lambda data: data[\"martinis_consumed\"].replace(\n",
774+
" -6, 6\n",
775+
" ),\n",
819776
" )\n",
820777
")"
821778
]
@@ -858,9 +815,7 @@
858815
"data = (\n",
859816
" james_bond_data.rename(columns=new_column_names)\n",
860817
" .combine_first(\n",
861-
" pd.DataFrame(\n",
862-
" {\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}}\n",
863-
" )\n",
818+
" pd.DataFrame({\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}})\n",
864819
" )\n",
865820
" .assign(\n",
866821
" income_usa=lambda data: (\n",
@@ -888,17 +843,18 @@
888843
" release_date=lambda data: pd.to_datetime(\n",
889844
" data[\"release_date\"], format=\"%B, %Y\"\n",
890845
" ),\n",
891-
" release_year=lambda data: data[\"release_date\"]\n",
892-
" .dt.year.astype(\"Int64\"),\n",
846+
" release_year=lambda data: data[\"release_date\"].dt.year.astype(\"Int64\"),\n",
893847
" bond_actor=lambda data: (\n",
894848
" data[\"bond_actor\"]\n",
895849
" .str.replace(\"Shawn\", \"Sean\")\n",
896850
" .str.replace(\"MOORE\", \"Moore\")\n",
897851
" ),\n",
898-
" car_manufacturer=lambda data: data[\"car_manufacturer\"]\n",
899-
" .str.replace(\"Astin\", \"Aston\"),\n",
900-
" martinis_consumed=lambda data: data[\"martinis_consumed\"]\n",
901-
" .replace(-6, 6),\n",
852+
" car_manufacturer=lambda data: data[\"car_manufacturer\"].str.replace(\n",
853+
" \"Astin\", \"Aston\"\n",
854+
" ),\n",
855+
" martinis_consumed=lambda data: data[\"martinis_consumed\"].replace(\n",
856+
" -6, 6\n",
857+
" ),\n",
902858
" )\n",
903859
" .drop_duplicates(ignore_index=True)\n",
904860
")"
@@ -931,7 +887,7 @@
931887
"metadata": {},
932888
"outputs": [],
933889
"source": [
934-
" data[\"bond_actor\"].value_counts()"
890+
"data[\"bond_actor\"].value_counts()"
935891
]
936892
},
937893
{
@@ -1085,7 +1041,7 @@
10851041
"ax.set_title(\"Scatter Plot of Kills vs Ratings\")\n",
10861042
"ax.set_xlabel(\"Average IMDb Rating\")\n",
10871043
"ax.set_ylabel(\"Kills by Bond\")\n",
1088-
"#fig.show()"
1044+
"# fig.show()"
10891045
]
10901046
}
10911047
],

‎data-analysis/data_analysis_results.ipynb‎

Lines changed: 8 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -49,9 +49,7 @@
4949
"data = (\n",
5050
" james_bond_data.rename(columns=new_column_names)\n",
5151
" .combine_first(\n",
52-
" pd.DataFrame(\n",
53-
" {\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}}\n",
54-
" )\n",
52+
" pd.DataFrame({\"imdb\": {10: 7.1}, \"rotten_tomatoes\": {10: 6.8}})\n",
5553
" )\n",
5654
" .assign(\n",
5755
" income_usa=lambda data: (\n",
@@ -79,18 +77,18 @@
7977
" release_date=lambda data: pd.to_datetime(\n",
8078
" data[\"release_date\"], format=\"%B, %Y\"\n",
8179
" ),\n",
82-
" release_year=lambda data: data[\"release_date\"]\n",
83-
" .dt.year\n",
84-
" .astype(\"Int64\"),\n",
80+
" release_year=lambda data: data[\"release_date\"].dt.year.astype(\"Int64\"),\n",
8581
" bond_actor=lambda data: (\n",
8682
" data[\"bond_actor\"]\n",
8783
" .str.replace(\"Shawn\", \"Sean\")\n",
8884
" .str.replace(\"MOORE\", \"Moore\")\n",
8985
" ),\n",
90-
" car_manufacturer=lambda data: data[\"car_manufacturer\"]\n",
91-
" .str.replace(\"Astin\", \"Aston\"),\n",
92-
" martinis_consumed=lambda data: data[\"martinis_consumed\"]\n",
93-
" .replace(-6, 6),\n",
86+
" car_manufacturer=lambda data: data[\"car_manufacturer\"].str.replace(\n",
87+
" \"Astin\", \"Aston\"\n",
88+
" ),\n",
89+
" martinis_consumed=lambda data: data[\"martinis_consumed\"].replace(\n",
90+
" -6, 6\n",
91+
" ),\n",
9492
" )\n",
9593
" .drop_duplicates(ignore_index=True)\n",
9694
")\n",

0 commit comments

Comments
 (0)