Add script for checking fasttext vocab

check_fasttext_vocab.py

+"""Find out vocab counts and positions for names in
+names lists, in German fasttext model."""
+
+import fasttext
+import pandas as pd
+
+df = pd.read_csv("../data/names_nationality_data.csv")
+df["in_fasttext_vocab"] = 0
+
+model = fasttext.load_model("cc.de.300.bin")
+
+for index, row in df.iterrows():
+    name = row['name']
+    if name in model.words:
+        df.at[index, "in_fasttext_vocab"] = 1
+
+df.to_csv("../data/names_nationality_fasttext.csv", index=False)