def main():
# ``range()`` returns a list ...
with memory_usage() as u:
x = range(10 * 1000 * 1000)
# ... so in our case the memory used by this process will be quite higher
# now.
print "range(): %s" % (u.rss,)
# ``xrange()``, in contrast, returns an *iterator* ...
with memory_usage() as u:
x = xrange(10 * 1000 * 1000)
# ... so now there should be almost no memory increase.
print "xrange(): %s" % (u.rss,)
def main():
for x, y in zip(xrange(1000), my_range(1000)):
if x != y:
raise Exception("Oops: %d is not %d" % (x, y))
# ``my_range()`` returns an iterator, too ...
with memory_usage() as u:
x = my_range(10 * 1000 * 1000)
# ... so now there should be almost no memory increase.
print "my_range(): %s" % (u.rss,)
def iterate_on_transactions(training=training, version=1):
if version == 1:
print("iterate on transactions")
path_to_csv = path_to_data + 'transactions.csv'
else:
print("iterate on transactions_v2")
path_to_csv = path_to_data + 'transactions_v2.csv'
i = 0
df_iter = pd.read_csv(path_to_csv, low_memory=False, iterator=True,
chunksize=transactions_chunk_size)
print("starting iteration...")
for transactions in df_iter:
print("i=" + str(i))
transactions = reformat_transactions(transactions)
user_count = Counter(transactions['msno']).most_common()
user_count = pd.DataFrame(user_count)
user_count.columns = ['msno', 'current_number_of_transactions']
user_count.set_index('msno', inplace=True)
training = pd.merge(left=training, right=user_count, how='left', left_index=True, right_index=True)
training['current_number_of_transactions'] = training.current_number_of_transactions.apply(
lambda x: int(x) if pd.notnull(x) else 0)
training["total_number_of_transactions"] += training["current_number_of_transactions"]
training.drop(['current_number_of_transactions'], axis=1, inplace=True)
print("memory usage of training: ")
print(memory_usage(training))
print("memory usage of transactions: ")
print(memory_usage(transactions))
i += 1
print("end of iteration...")
i = 0
training.reset_index(inplace=True)
training_copy = training.copy()
df_iter = pd.read_csv(path_to_data + 'transactions.csv', low_memory=False, iterator=True,
chunksize=transactions_chunk_size)
print("starting iteration, looking for most recent transaction...")
for transactions in df_iter:
print("i=" + str(i))
reformat_transactions(transactions)
recent_transactions = transactions.sort_values(['transaction_date']).groupby('msno').first()
recent_transactions.reset_index(inplace=True)
temp_training = pd.merge(left=training_copy, right=recent_transactions, how='right', on=['msno'], right_index=True)
training = pd.concat((training, temp_training))
training = training.sort_values(['transaction_date']).groupby('msno').first()
print("memory usage of training: ")
print(memory_usage(training))
print("memory usage of transactions: ")
print(memory_usage(transactions))
i += 1
del training_copy
i = 0
df_iter = pd.read_csv(path_to_data + 'transactions.csv', low_memory=False, iterator=True,
chunksize=transactions_chunk_size)
training["price_per_day"] = training["actual_amount_paid"]/(training["payment_plan_days"]+0.01)
print("starting iteration, looking for usual price per day...")
for transactions in df_iter:
print("i=" + str(i))
i += 1
transactions = reformat_transactions(transactions)
transactions["current_price_per_day"] = transactions["actual_amount_paid"] / (transactions["payment_plan_days"] + 0.01)
transactions = transactions.groupby("msno").sum()
columns_to_keep = ["current_price_per_day"]
transactions = transactions[columns_to_keep]
training = pd.merge(left=training, right=transactions, how='left', left_index=True, right_index=True)
training["usual_price_per_day"] += training["current_price_per_day"]
training.drop(['current_price_per_day'], axis=1, inplace=True)
return training
