Merge branch 'master' of https://gitlab.com/usi-si-teaching/msde/2022-2023/visual-analytics-atelier/group-projects/group-1

.vscode/settings.json

@@ -1,6 +1,6 @@
 {
     "[python]": {
-        "editor.defaultFormatter": "ms-python.autopep8"
+        "editor.defaultFormatter": "ms-python.python"
     },
     "python.formatting.provider": "none"
 }

backend/api/companies.py

@@ -0,0 +1,24 @@
+import os
+import pandas as pd
+import numpy as np
+from scraper.top100_extractor import programming_crime_list
+COMPANIES_CSV_PATH: str = 'scraper/companies.csv'
+
+def non_nan(a: list[any]) -> list[any]:
+    return list(filter(lambda a: type(a) == str or not np.isnan(a), a))
+
+
+def get_companies(root_dir: str) -> list[dict]:
+    """ 
+    reads the companies.csv file and returns it as a JSON-ifiable object 
+    to return to the frontend.
+    """
+    df = pd.read_csv(os.path.join(root_dir, COMPANIES_CSV_PATH), index_col='ticker')
+    tickers = pd.Series(programming_crime_list)
+    df = df.loc[df.index.isin(tickers), :]
+    df['tags'] = df[['tag 1', 'tag 2', 'tag 3']].values.tolist()
+    df['tags'] = df['tags'].apply(non_nan)
+    del df['tag 1']
+    del df['tag 2']
+    del df['tag 3']
+    return df.reset_index().replace({ np.nan: None }).to_dict('records')