def write_rts_model(model, key, connection_string):
RTS_odbc = RxOdbcData(connection_string, table="RTS")
serialized_model = rx_serialize_model(model, realtime_scoring_only=True)
rx_write_object(RTS_odbc,
key=key,
value=serialized_model,
serialize=False,
compress=None,
overwrite=True)
model_type = "linear"
conn_str = 'Driver=SQL Server;Server=<Server Name>;Database=MLDB;Uid=<User Name>;Pwd=<Password>;'
cnxn = pyodbc.connect(conn_str)
inputsql = 'select "RentalCount", "Year", "Month", "Day", "WeekDay", "Snow", "Holiday", "FWeekDay" from dbo.rental_data where Year < 2015'
rental_train_data = pd.read_sql(inputsql, cnxn)
# Used to sample data
# train = rental_train_data.sample(frac=0.8, random_state=1)
# test = rental_train_data.loc[~ rental_train_data.index.isin(train.index)]
# print("Train {0} / test {1}".format(len(train), len(test)))
rental_train_data["Holiday"] = rental_train_data["Holiday"].astype("category")
rental_train_data["Snow"] = rental_train_data["Snow"].astype("category")
rental_train_data["WeekDay"] = rental_train_data["WeekDay"].astype("category")
if model_type == "linear":
linmod_model = rx_lin_mod("RentalCount ~ Month + Day + WeekDay + Snow + Holiday", data = rental_train_data)
trained_model = rx_serialize_model(linmod_model, realtime_scoring_only = True)
if model_type == "dtree":
dtree_model = rx_dtree("RentalCount ~ Month + Day + WeekDay + Snow + Holiday", data = rental_train_data)
trained_model = rx_serialize_model(dtree_model, realtime_scoring_only = True)
print(rx_summary("~ Month + Day + WeekDay + Snow + Holiday", rental_train_data))
# Dump learned model to file
with open(r'c:\temp\trained_model.pickle', mode='wb') as f:
f.write(trained_model)
cursor=cnxn.cursor()
cursor.execute("INSERT INTO rental_models(model_name, lang, native_model) VALUES(?, ?, ?)", (model_type + "_model", "Python", trained_model))
cnxn.commit()
conn_str = 'Driver=SQL Server;Server=SoL01.techsummit.local;Database=MLDB;Uid={0};Pwd={1};'.format("sa",os.getenv("SQLPass"))
cnxn = pyodbc.connect(conn_str)
inputsql ='''
SELECT C1, C2 FROM (
VALUES
('A',1),('B',2),('C',3),('D',4),('E',5),('F',6),('G',7),('H',8),('I',9),('J',10),
('K',11),('L',12),('M',13),('N',14),('O',15),('P',16),('Q',17),('R',18),('S',19),('T',20),
('U',21),('V',22),('W',23),('X',24),('Y',25),('Z',26)
) AS T1(C1, C2)
'''
train_data = pd.read_sql(inputsql, cnxn)
train_data["C1"] = train_data["C1"].astype("category")
print(train_data["C1"] )
# model = rx_lin_mod("C2 ~ C1", data = train_data)
model = rx_fast_linear("C2 ~ C1", data = train_data, method = "regression")
print(rx_summary("C2 ~ C1", train_data))
trained_model = rx_serialize_model(model, realtime_scoring_only = True)
# Dump learned model to file
with open(r'c:\temp\trained_model_{0}.pickle'.format(model_file), mode='wb') as f:
f.write(trained_model)
p_data = pd.DataFrame([0,5,10,99,4], columns=["C1"])
p_data["C1"] = train_data["C1"].astype("category")
print(p_data["C1"])
pred = rx_predict(model, data = p_data)
print(pred)