def test_output_contains_extra_columns(self):
"""Output should contain extra columns when topn > 1."""
stock = [{"text": "circuit", "id": "1", "Brand": ""}]
output = add_commodities_to_stocks(stock, topn=3)
assert all([
key in output[0][0]
for key in ("Jaccard", "Jaccard 2", "Jaccard 3",
"Commodity Code 2", "Commodity 3")
])
def test_regression(self):
"""Rerun code on regression_test_stock_master.csv and make sure the results match."""
#print(sys.path)
stock_master = read_csv("regression_test_stock_master.csv")
rows, fieldnames = commodity_matcher.add_commodities_to_stocks(stock_master[:100])
all_matched = True
for i, row in enumerate(rows):
if not row['Commodity'] == stock_master[i]['Commodity']:
print("Did not match, row "+str(i)+", "+row['text'])
print("New: '"+row['Commodity']+"' vs. Original: '"+stock_master[i]['Commodity']+"'")
all_matched = False
assert(len(rows) == 100)
assert(sorted(rows[0].keys()) == sorted(fieldnames))
assert(sorted(fieldnames) == sorted(stock_master[0].keys()))
if not all_matched:
print("WARNING: all of the rows did not match. If the above results look fine, you may want to update regression_test_stock_master.csv.")
def api():
if request.method == "GET":
brand = request.args.get("brand", default="")
text = request.args.get("description")
rows = [{"Brand": brand, "id": "1", "text": text}]
results = commodity_matcher.add_commodities_to_stocks(rows)
msg = "Success!"
return {
"Results": results[0],
"Errors": [],
"Status": "finished",
"Message": msg
}
else:
data = request.json
rows = []
for i, row in enumerate(data["rows"]):
if "brand" in row:
brand = row["brand"]
else:
brand = ""
rows.append({
"Brand": brand,
"id": str(i),
"text": row["description"]
})
row_hash = str(hash(json.dumps(rows)))
try:
j = Job.fetch(row_hash, conn)
status = j.get_status()
if status == "finished":
if isinstance(j.result, Exception):
print(j.result)
msg = "Something went wrong and now everything is on fire."
return {
"Results": [],
"Errors": [str(j.result)],
"Status": status,
"Message": msg
}
else:
msg = "Success!"
return {
"Results": j.result[0],
"Errors": [],
"Status": status,
"Message": msg
}
else:
msg = "Processing. Ask again in a few minutes to see your results."
if status == "failed":
msg = "Time limit exceeded. Try a smaller job."
return {
"Results": [],
"Errors": [],
"Status": status,
"Message": msg
}
except NoSuchJobError:
j = q.enqueue(commodity_matcher.add_commodities_to_stocks,
rows,
job_id=row_hash)
msg = "Processing. Ask again in a few minutes to see your results."
return {
"Results": [],
"Errors": [],
"Status": j.get_status(),
"Message": msg
}
def test_should_not_affect_input(self):
"""Should not modify input list in place."""
stock = [{"text": "circuit", "id": "1", "Brand": ""}]
stock_copy = copy.deepcopy(stock)
output = add_commodities_to_stocks(stock)
assert stock == stock_copy
def test_output_contains_all_input_keys(self):
"""All keys in input dictionaries should also exist in output dictionaries."""
stock = [{"text": "circuit", "id": "1", "Brand": ""}]
output = add_commodities_to_stocks(stock)
assert all([key in output[0][0] for key in stock[0]])