def merge_dicts(ionization, isotopes):
element_data = dict()
# Processes Ionization Levels
for elem, ion in ionization.iteritems():
symbol = SYMBOL_MAPPING.get(elem.lower(), elem.lower())
ion = lower_keys(ion)
ion['protons'] = ion['atomic number']
ion = dict(sorted(ion.items()))
element_data[symbol] = ion
# Process Isotopes
for elem, isotope in isotopes.iteritems():
symbol = SYMBOL_MAPPING.get(elem.lower(), elem.lower())
isotope = lower_keys(isotope)
isotope = dict(sorted(isotope.items()))
isotope["isotopes"] = isotope.pop("isotopes")
if "standard atomic weight" in isotope:
set_value(
element_data[symbol],
["atomic weight", "atomic mass", "mass", "amu", "weight"],
isotope["standard atomic weight"])
for each in isotope["isotopes"]:
each = lower_keys(each)
set_value(
each,
["atomic weight", "atomic mass", "mass", "amu", "weight"],
each["relative atomic mass"])
mass_number = each["mass number"]
if symbol in element_data:
element_data[symbol][mass_number] = dict(sorted(each.items()))
return element_data
def search(self, query):
numbers = filter_numbers(query.lower())
keywords = [numbers] + [
SYMBOL_MAPPING.get(key, key)
for key in indicoio.keywords(" ".join(map(preformat, query.lower().split(" "))), top_n=100).keys()
]
keywords = " ".join(keywords)
best = 0
results = []
for key in KEYWORDS:
# ratio = fuzz.token_set_ratio(keywords, key)
ratio = 0
for word in keywords.split(" "):
keys = key.split(" ")
if word in keys:
ratio += 1
if ratio > best:
best = ratio
results = []
results.append((ratio, key, data.ELEMENT_DATA[key]))
elif ratio == best:
results.append((ratio, key, data.ELEMENT_DATA[key]))
if len(results) > 3:
for i in xrange(len(results)):
results[i] = fuzz.ratio(keywords, results[i][1]), results[i][1], results[i][2]
self.respond([{result[1]: result[2]} for result in sorted(results, reverse=True)[:5]])
def preformat(entry):
entry = entry.strip()
entry = SYMBOL_MAPPING.get(entry, entry)
result = spelling(entry)
if not result:
return ""
return result
def create_trie():
dictionary = load(os.path.join(OUTPUT_DIR, "element_data.p"))
# read dictionary file into a trie
trie = TrieNode()
words = []
for key in dictionary:
words += key.split(" ")
for key in set(words):
trie.insert(key)
for key in SYMBOL_MAPPING.keys():
trie.insert(key)
cache(trie, os.path.join(OUTPUT_DIR, "trie.p"))
