MSConcept Graph

_COURSE_CONCEPTS = {
    "economy": {"economy": 0.8, "business": 0.2},
    "market": {"economy": 0.7, "business": 0.3},
    "country": {"nation": 0.8, "place": 0.2},
    "nation": {"nation": 0.8, "place": 0.2},
    "president": {"person": 0.8, "leader": 0.2},
    "leader": {"person": 0.7, "official": 0.3},
    "technology": {"technology": 0.8, "topic": 0.2},
}

def query(value):
    for word in str(value).lower().replace("_", " ").split():
        if word in _COURSE_CONCEPTS:
            return dict(_COURSE_CONCEPTS[word])
    return {"topic": 1.0}

query("microsoft")

all_titles = [
    "National economy improves as the market creates new jobs",
    "Business leaders discuss the economy and responsible investment",
    "The president presents a national technology strategy",
    "A regional leader announces support for local businesses",
    "The nation expands training for technology workers",
    "Market reforms support the economy and small business",
    "The president meets a foreign leader for policy talks",
    "Technology investment strengthens the national economy",
]

all_titles

import re

class TextBlob:
    def __init__(self, text):
        self.text = text

    @property
    def noun_phrases(self):
        words = re.findall(r"[a-z]+", self.text.lower())
        return [word for word in words if word in {"economy", "market", "business", "nation", "national", "president", "leader", "technology"}]

w = {}
for x in all_titles:
    for n in TextBlob(x).noun_phrases:
        if n in w:
            w[n].append(x)
        else:
            w[n]=[x]
{ x:len(w[x]) for x in w.keys()}

w = {}
for x in all_titles:
    for noun in TextBlob(x).noun_phrases:
        terms = query(noun)
        for term in [u for u in terms.keys() if terms[u]>0.1]:
            if term in w:
                w[term].append(x)
            else:
                w[term]=[x]

{ x:len(w[x]) for x in w.keys() if len(w[x])>3}

print('\nECONOMY:\n'+'\n'.join(w['economy']))
print('\nNATION:\n'+'\n'.join(w['nation']))
print('\nPERSON:\n'+'\n'.join(w['person']))