def cleaning_reg_ex(data=loading_data()):
regex = re.compile(r"\[|\]|<", re.IGNORECASE)
data.columns = [
regex.sub("_", col) if any(x in str(col) for x in set(("[", "]", "<"))) else col
for col in data.columns.values
]
return data
def test_loading_data_return_numberColumns():
output = loading_data()
CSV = pd.read_csv(
"https://ndownloader.figshare.com/files/20976540",
index_col="instant",
parse_dates=True,
)
expected_output = len(CSV.columns)
assert len(output.columns) == expected_output
def test_loading_data_retur_describe():
output = loading_data()
CSV = pd.read_csv(
"https://ndownloader.figshare.com/files/20976540",
index_col="instant",
parse_dates=True,
)
expected_output = print(CSV.dtypes)
assert print(output.dtypes) == expected_output
def test_train_split(data=whole_preprocessing(loading_data())):
hour_d_train = data.iloc[0:15211]
hour_d_test = data.iloc[15212:17379]
hour_d_train = hour_d_train.drop(
columns=["dteday", "casual", "atemp", "registered"])
hour_d_test = hour_d_test.drop(
columns=["dteday", "casual", "registered", "atemp"])
# seperate the independent and target variable on testing data
hour_d_train_x = hour_d_train.drop(columns=["cnt"], axis=1)
hour_d_train_y = hour_d_train["cnt"]
# seperate the independent and target variable on test data
hour_d_test_x = hour_d_test.drop(columns=["cnt"], axis=1)
hour_d_test_y = hour_d_test["cnt"]
return hour_d_train_x, hour_d_train_y, hour_d_test_x, hour_d_test_y
def feature_engeneering(data=loading_data()):
data["IsOfficeHour"] = np.where(
(data["hr"] >= 9) & (data["hr"] < 17) & (data["weekday"] == 1), 1, 0
)
data["IsDaytime"] = np.where((data["hr"] >= 6) & (data["hr"] < 22), 1, 0)
data["IsRushHourMorning"] = np.where(
(data["hr"] >= 6) & (data["hr"] < 10) & (data["weekday"] == 1), 1, 0
)
data["IsRushHourEvening"] = np.where(
(data["hr"] >= 15) & (data["hr"] < 19) & (data["weekday"] == 1), 1, 0
)
data["IsHighSeason"] = np.where((data["season"] == 3), 1, 0)
bins = [0, 0.19, 0.49, 0.69, 0.89, 1]
data["temp_binned"] = pd.cut(data["temp"], bins)
data["hum_binned"] = pd.cut(data["hum"], bins)
return data
def convert_to_category(data=loading_data()):
convert_to_category = [
"season",
"yr",
"mnth",
"hr",
"holiday",
"weekday",
"workingday",
"weathersit",
"IsOfficeHour",
"IsDaytime",
"IsRushHourMorning",
"IsRushHourEvening",
"IsHighSeason",
"temp_binned",
"hum_binned",
]
for col in convert_to_category:
data[col] = data[col].astype("category")
return data
def test_predict_data_cols_len():
output = len(whole_preprocessing(loading_data()).columns)
expected_output = 85
assert output == expected_output
def test_predict_output_len():
output = len(predict(loading_data()))
expected_output = 21
assert output == expected_output
def test_predict_type():
output = type(predict(loading_data()))
expected_output = str
assert output == expected_output
def test_loading_data_return_DF():
output = loading_data()
assert type(output) is pd.DataFrame
def test_predict_data_rows_len():
output = len(whole_preprocessing(loading_data()))
expected_output = 17379
assert output == expected_output
def test_test_train_split_column_length(data=whole_preprocessing(
loading_data())):
col_num = test_train_split(data)[0]
output = len(col_num.columns)
expected_output = 80
assert output == expected_output
def test_test_train_split_length(data=whole_preprocessing(loading_data())):
output = len(test_train_split(data)[0])
expected_output = 15211
assert output == expected_output
def get_dummies(data=loading_data()):
data = pd.get_dummies(data)
return data
def test_test_train_split_target_type(data=whole_preprocessing(
loading_data())):
cnt = test_train_split(data)[1]
output = type(cnt)
expected_output = pd.core.series.Series
assert output == expected_output
def test_test_train_split_length_tuple(data=whole_preprocessing(
loading_data())):
output = len(test_train_split(data))
expected_output = 4
assert output == expected_output
def test_test_train_split_train_not_cnt(data=whole_preprocessing(
loading_data())):
output = test_train_split(data)[2].columns
expected_output = "cnt"
assert expected_output not in output
def skewness(data=loading_data()):
data["windspeed"] = np.log1p(data.windspeed)
data["cnt"] = np.sqrt(data.cnt)
return data
def convert_date_time(data=loading_data()):
data["dteday"] = pd.to_datetime(data["dteday"])
return data
def test_test_train_split(data=whole_preprocessing(loading_data())):
output = test_train_split(data)
assert type(output) is tuple
