Sorted imports with isort & Autoformat code with Black

Author: github-actions[bot]

dag/flows/healthcheck.py

@@ -1,8 +1,9 @@
 import platform
-import prefect
-from prefect import task, flow, get_run_logger
 import sys
 
+import prefect
+from prefect import flow, get_run_logger, task
+
 
 @task
 def log_platform_info():

get_version.py

@@ -1,4 +1,5 @@
 import warnings
+
 import versioneer
 
 if __name__ == "__main__":

notebooks/data_exploration.ipynb

@@ -339,9 +339,9 @@
     }
    ],
    "source": [
-    "with open(os.path.join(Path.sql_queries, 'get_all_game_data.sql'), \"r\") as f:\n",
+    "with open(os.path.join(Path.sql_queries, \"get_all_game_data.sql\"), \"r\") as f:\n",
     "    query = text(f.read())\n",
-    "    \n",
+    "\n",
     "\n",
     "with get_db() as db:\n",
     "    result = db.execute(query)\n",
@@ -371,7 +371,7 @@
     }
    ],
    "source": [
-    "game_data['description'].iloc[10000-4-1]"
+    "game_data[\"description\"].iloc[10000 - 4 - 1]"
    ]
   },
   {
@@ -396,6 +396,7 @@
    "source": [
     "from fuzzywuzzy import process\n",
     "\n",
+    "\n",
     "def get_unique(series):\n",
     "    \"\"\"\n",
     "    Returns a set of unique values from a series of strings.\n",
@@ -407,7 +408,7 @@
     "    set: A set of unique values extracted from the series.\n",
     "\n",
     "    \"\"\"\n",
-    "    return set(list(itertools.chain(*series.apply(lambda x: [c for c in x.split(';')]))))"
+    "    return set(list(itertools.chain(*series.apply(lambda x: [c for c in x.split(\";\")]))))"
    ]
   },
   {
@@ -461,7 +462,7 @@
     }
    ],
    "source": [
-    "geners = get_unique(game_data['genres'])\n",
+    "geners = get_unique(game_data[\"genres\"])\n",
     "geners"
    ]
   },
@@ -494,28 +495,30 @@
     "def standardize_genre(value, genre_list):\n",
     "    # Convert to lowercase for consistent comparison\n",
     "    value_lower = value.lower()\n",
-    "    \n",
+    "\n",
     "    # Define common patterns\n",
-    "    if 'rpg' in value_lower or 'role playing' in value_lower or 'role' in value_lower:\n",
-    "        return 'RPG'\n",
-    "    if 'simulation' in value_lower or 'simulators' in value_lower:\n",
-    "        return 'Simulation'\n",
-    "    if 'adventure' in value_lower:\n",
-    "        return 'Adventure'\n",
+    "    if \"rpg\" in value_lower or \"role playing\" in value_lower or \"role\" in value_lower:\n",
+    "        return \"RPG\"\n",
+    "    if \"simulation\" in value_lower or \"simulators\" in value_lower:\n",
+    "        return \"Simulation\"\n",
+    "    if \"adventure\" in value_lower:\n",
+    "        return \"Adventure\"\n",
+    "\n",
     "\n",
     "# Function to standardize multiple genres\n",
     "def standardize_multiple_genres(genres_str, genre_list):\n",
-    "    genres = genres_str.split(';')\n",
+    "    genres = genres_str.split(\";\")\n",
     "    standardized_genres = [standardize_genre(genre.strip(), genre_list) for genre in genres]\n",
-    "    return ';'.join(sorted(set(standardized_genres)))  # Use sorted(set()) to remove duplicates and sort\n",
-    "    \n",
+    "    return \";\".join(sorted(set(standardized_genres)))  # Use sorted(set()) to remove duplicates and sort\n",
+    "\n",
     "    # Find the best match from the list of unique genres\n",
     "    match, score = process.extractOne(value, genre_list)\n",
     "    return match\n",
     "\n",
+    "\n",
     "# Apply the standardization function to the Genres column\n",
-    "game_data['genres'] = game_data['genres'].apply(lambda x: standardize_multiple_genres(x, geners))\n",
-    "geners = get_unique(game_data['genres'])\n",
+    "game_data[\"genres\"] = game_data[\"genres\"].apply(lambda x: standardize_multiple_genres(x, geners))\n",
+    "geners = get_unique(game_data[\"genres\"])\n",
     "geners"
    ]
   },
@@ -615,7 +618,7 @@
     }
    ],
    "source": [
-    "categories = get_unique(game_data['categories'])\n",
+    "categories = get_unique(game_data[\"categories\"])\n",
     "categories"
    ]
   },
@@ -643,21 +646,22 @@
     "    - score: The calculated rating score as a percentage.\n",
     "\n",
     "    \"\"\"\n",
-    "    pos = row['positive_ratings']\n",
-    "    neg = row['negative_ratings']\n",
+    "    pos = row[\"positive_ratings\"]\n",
+    "    neg = row[\"negative_ratings\"]\n",
     "\n",
     "    total_reviews = pos + neg\n",
-    "    \n",
+    "\n",
     "    if total_reviews > 0:\n",
     "        average = pos / total_reviews\n",
-    "        score = average - (average * 0.5) * 2**(-math.log10(total_reviews + 1))\n",
+    "        score = average - (average * 0.5) * 2 ** (-math.log10(total_reviews + 1))\n",
     "        return score * 100\n",
     "    else:\n",
     "        return 0.0\n",
     "\n",
-    "game_data['total_ratings'] = game_data['positive_ratings'] + game_data['negative_ratings']\n",
-    "game_data['review_score'] = game_data['positive_ratings'] / game_data['total_ratings']\n",
-    "game_data['rating'] = game_data.apply(calc_rating, axis=1)"
+    "\n",
+    "game_data[\"total_ratings\"] = game_data[\"positive_ratings\"] + game_data[\"negative_ratings\"]\n",
+    "game_data[\"review_score\"] = game_data[\"positive_ratings\"] / game_data[\"total_ratings\"]\n",
+    "game_data[\"rating\"] = game_data.apply(calc_rating, axis=1)"
    ]
   },
   {
@@ -996,24 +1000,25 @@
    "source": [
     "def categorize_year(year):\n",
     "    if year < 2020:\n",
-    "        return 'Before 2020'\n",
+    "        return \"Before 2020\"\n",
     "    elif 2020 <= year <= 2022:\n",
-    "        return '2020-2022'\n",
+    "        return \"2020-2022\"\n",
     "    else:\n",
-    "        return 'After 2022'\n",
+    "        return \"After 2022\"\n",
+    "\n",
     "\n",
-    "game_data['year'] = game_data['year'].fillna(0).astype(int) \n",
-    "game_data['Region'] = game_data['year'].apply(categorize_year)\n",
+    "game_data[\"year\"] = game_data[\"year\"].fillna(0).astype(int)\n",
+    "game_data[\"Region\"] = game_data[\"year\"].apply(categorize_year)\n",
     "\n",
     "# Calculate the frequency of each year\n",
-    "yearly_counts = game_data.groupby(['Region', 'year']).size().reset_index(name='Frequency')\n",
+    "yearly_counts = game_data.groupby([\"Region\", \"year\"]).size().reset_index(name=\"Frequency\")\n",
     "\n",
     "# Plotting using Seaborn\n",
     "plt.figure(figsize=(12, 6))\n",
-    "sns.barplot(data=yearly_counts, x='year', y='Frequency', hue='Region')\n",
-    "plt.title('Game Release by Year')\n",
-    "plt.xlabel('Year')\n",
-    "plt.ylabel('Frequency')\n",
+    "sns.barplot(data=yearly_counts, x=\"year\", y=\"Frequency\", hue=\"Region\")\n",
+    "plt.title(\"Game Release by Year\")\n",
+    "plt.xlabel(\"Year\")\n",
+    "plt.ylabel(\"Frequency\")\n",
     "plt.xticks(rotation=45)\n",
     "plt.show()"
    ]
@@ -1031,12 +1036,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "tags = col_row_df['tags']\n",
+    "tags = col_row_df[\"tags\"]\n",
     "parsed_tags = tags.apply(lambda x: literal_eval(x) if x else {})\n",
     "\n",
     "unique_tags = set(itertools.chain(*parsed_tags))\n",
     "\n",
-    "print('Number of unique tags:', len(unique_tags))\n",
+    "print(\"Number of unique tags:\", len(unique_tags))\n",
     "\n",
     "# Create a DataFrame with 15 columns and 30 rows\n",
     "num_columns = 15\n",
@@ -1045,7 +1050,7 @@
     "unique_tags = sorted(list(unique_tags))\n",
     "\n",
     "# Reshape the list into the desired DataFrame shape\n",
-    "ut = [unique_tags[i * num_columns:(i + 1) * num_columns] for i in range(num_rows)]\n",
+    "ut = [unique_tags[i * num_columns : (i + 1) * num_columns] for i in range(num_rows)]\n",
     "\n",
     "# Create the DataFrame\n",
     "utdf = pd.DataFrame(ut)\n",
@@ -1079,8 +1084,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "langs = col_row_df['languages']\n",
-    "langs = langs.apply(lambda x: x.split(', ') if x else [])\n",
+    "langs = col_row_df[\"languages\"]\n",
+    "langs = langs.apply(lambda x: x.split(\", \") if x else [])\n",
     "\n",
     "langc = Counter()\n",
     "\n",