def delete_record(id_):
"""
Deletes one record based on it's ID.
If the ID given doesn't exist, nothing will be deleted.
"""
df = utils.read_dataframe()
df_altered = df[df['ID'] != id_]
utils.save_dataframe(data=df_altered)
return None
def add_record(name, age, fav_sport):
"""Adds one record to the database (CSV file)"""
df = utils.read_dataframe()
df_record_to_add = pd.DataFrame(data={
"ID": utils.generate_random_id(),
"Name": name,
"Age": age,
"FavouriteSport": fav_sport
}, index=[0])
df_concatenated = pd.concat(objs=[df, df_record_to_add], ignore_index=True, sort=False)
utils.save_dataframe(data=df_concatenated)
return None
def generate_first_file_hash():
index = 1
for i in range(1,11):
df = read_dataframe('2016-04-01', i)
df['hash'] = '000000'
for j in df.index:
df.set_value(j, 'hash', '{:06d}'.format(index))
index += 1
df.to_csv('/home/bobby/Documents/code/python/qishi/all_csv_with_hash/catagory{}/2016-04-01.csv'.format(i),
header = False, index=False)
# this index is the not used next index
return index
def get_record(id_):
"""
Gets one record (dictionary) based on it's ID.
If the ID given doesn't exist, returns empty dictionary.
"""
df = utils.read_dataframe()
df_record = df[df['ID'] == id_]
if df_record.empty:
return {}
if len(df_record) == 1:
dict_record = df_record.iloc[0].to_dict()
dict_record['Age'] = int(dict_record['Age'])
return dict_record
raise Exception("Multiple records with same ID exists")
def process(self, catagory):
self.catagory = catagory
last_date_data = read_dataframe_with_hash(self.start_date, self.catagory)
for current_date in date_range((self.start_date+timedelta(1)), self.end_date):
current_date_data = read_dataframe(current_date, self.catagory)
if current_date_data.empty:
continue
else:
current_date_data['hash'] = '000000'
solver = Solver(last_date_data, current_date_data, current_date, self.max_index)
self.max_index += solver.process()
solver.write_csv(self.catagory)
last_date_data = current_date_data
self.logger.info('{}: {}data have been completed'.format(datetime.now(), current_date))
print(self.max_index)
def update_record(id_, name=None, age=None, fav_sport=None):
"""
Updates one record based on it's ID, and some specified parameters.
If the ID given doesn't exist, nothing will be updated.
>>> update_record(id_="U0E4CXQSWC4S", name="SomeNewName", age=20, fav_sport="SomeNewFavouriteSport")
"""
df = utils.read_dataframe()
df_record_to_update = df[df['ID'] == id_]
if df_record_to_update.empty:
return None
if len(df_record_to_update) == 1:
if name:
df.loc[df['ID'] == id_, 'Name'] = name
if age:
df.loc[df['ID'] == id_, 'Age'] = age
if fav_sport:
df.loc[df['ID'] == id_, 'FavouriteSport'] = fav_sport
utils.save_dataframe(data=df)
return None
raise Exception("Multiple records with same ID exists")
def get_filtered_records(id_=None,
name=None,
age=None,
fav_sport=None,
min_age=None,
max_age=None):
"""Gets list of records filtered by criteria specified"""
df = utils.read_dataframe()
if id_:
df = df[df['ID'] == id_]
if name:
df = df[df['Name'] == name]
if age:
df = df[df['Age'] == age]
if fav_sport:
df = df[df['FavouriteSport'] == fav_sport]
if min_age:
df = df[df['Age'] >= min_age]
if max_age:
df = df[df['Age'] <= max_age]
if df.empty:
return []
return df.to_dict(orient='records')
import pandas
import sys
import utils
def normalize(dataframe):
return (dataframe - dataframe.mean()) / dataframe.std()
if __name__ == "__main__":
filename = sys.argv[1]
dataframe = utils.read_dataframe(filename)
for value in normalize(dataframe).values:
print value[0], value[1], value[2]
def get_all_records():
df = utils.read_dataframe()
return df.to_dict(orient='records')