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"))
for key, value in result.iteritems())
return dict((" ".join(sorted(set(key.split(" ")))), value)
for key, value in result.iteritems())
def parse_out_isotopes(data):
for key, value in data.iteritems():
if key in ELEMENT_MAPPING:
isotopes = []
for k in value.keys():
try:
val = int(str(k))
assert val == float(str(k))
isotopes.append((k, value.pop(k)))
except:
pass
if isotopes:
data[key]["isotopes"] = dict(isotopes)
return data
if __name__ == "__main__":
result = merge_dicts(
load(os.path.join(OUTPUT_DIR, "atomic_ionization_output.p")),
load(os.path.join(OUTPUT_DIR, "atomic_weight_compositions.p")))
look_up = get_the_big_dict(parse_out_isotopes(result))
print "\n".join(look_up.keys())
print look_up["hydrogen"]
cache(look_up, os.path.join(OUTPUT_DIR, "element_data.p"))
columns = len( word ) + 1
currentRow = [ previousRow[0] + 1 ]
# Build one row for the letter, with a column for each letter in the target
# word, plus one for the empty string at column 0
for column in xrange( 1, columns ):
insertCost = currentRow[column - 1] + 1
deleteCost = previousRow[column] + 1
if word[column - 1] != letter:
replaceCost = previousRow[ column - 1 ] + 1
else:
replaceCost = previousRow[ column - 1 ]
currentRow.append( min( insertCost, deleteCost, replaceCost ) )
# if the last entry in the row indicates the optimal cost is less than the
# maximum cost, and there is a word in this trie node, then add it.
if currentRow[-1] <= maxCost and node.word != None:
results[currentRow[-1]] = results.get(currentRow[-1], []) + [node.word]
# if any entries in the row are less than the maximum cost, then
# recursively search each branch of the trie
if min( currentRow ) <= maxCost:
for letter in node.children:
searchRecursive( node.children[letter], letter, word, currentRow,
results, maxCost )
create_trie()
trie = load(os.path.join(OUTPUT_DIR, "trie.p"))
""" Where the data lives loaded in memory because we don't like databases """ import os from blank.data_utils import load, OUTPUT_DIR ELEMENT_DATA = load(os.path.join(OUTPUT_DIR, "element_data.p"))