def test_find_lat_long(self):
city_lat_long = load_city_lat_long()
df = preprocess(load_data)
for city_key in list(df.CityCountry.unique()):
if city_key in city_lat_long:
print(city_lat_long[city_key])
def test_load_data(self):
df = preprocess(load_data)
# check temperature values
self.assertEqual(df.loc[df.AvgTemperature < -100, "AvgTemperature"].count(), 0)
self.assertEqual(df.loc[df.AvgTemperature > 200, "AvgTemperature"].count(), 0)
non_null_cols = df.drop(columns=["State", "AvgTemperature"])
nan_rows = non_null_cols[non_null_cols.isnull().T.any()]
# check for nan, nulls, empty str
self.assertEqual(
len(nan_rows),
0,
nan_rows,
)
city_country = df["CityCountry"]
self.assertFalse(city_country.isnull().any().any())
self.assertEqual(
len(np.where(city_country == "")[0]),
0,
np.where(city_country == "")[0],
)
def positive_negative_samples_test():
Z = []
#sample number in DD.mat dataset
x = 2
i = 0
# i defines the number of samples variations we want to create for a matrix
while i < 20:
#append the xth Adj matrix from dataset
Z.append(preprocess(x))
i += 1
# starting to make variations to all matrix except first one
j = 1
while j < 20:
#generate negative/positive samples and modify the Z[j] matrix
#generate_negative(Z[j])
generate_positive(Z[j])
j += 1
i = 0
#comparing with all negative matrices
j = 1
while j < 20:
Z1_x = nx.from_numpy_matrix(Z[i])
Z2_x = nx.from_numpy_matrix(Z[j])
# compute the laplacian and eigen values
lap1 = eig(Z1_x, "eigvalsh")
lap2 = eig(Z2_x, "eigvalsh")
#import ipdb; ipdb.set_trace()
print('Variation {} - {}'.format(
j, 1 - spatial.distance.cosine(lap1, lap2)))
print('Variation {} - {}'.format(j, distance.euclidean(lap1, lap2)))
print('Variation {} - {}'.format(j, distance.minkowski(lap1, lap2)))
j += 1
from process_data import preprocess, load_data
from render_charts import vis_data
def print_info(df):
print(df.dtypes)
print(df.describe(datetime_is_numeric=True))
# print(df.Date.dt.day.explode().value_counts())
print(df.drop(columns=["State"]).isnull().sum())
print(df.drop(columns=["State"])[df["AvgTemperature"].isna()])
cites_num = len(df["City"].unique())
print(
f"This data contains a list of daily average temperatures from {cites_num} cities and {len(df['Country'].unique())} countries."
)
if __name__ == "__main__":
df = preprocess(load_data())
print_info(df)
def test_snapshot_match(self):
df = preprocess(load_data)
self.assertMatchSnapshot(df.info(), "df_info")
self.assertMatchSnapshot(df.describe(datetime_is_numeric=True), "df_describe")
def test_calc_monthly(self):
df = preprocess(load_data)
# check columns
calc_monthly(build_city_df(df, "Abilene, Texas, US", False))
def test_build_city_df(self):
df = preprocess(load_data)
# check columns
self.assertRaises(LookupError, build_city_df, df, "test", False)
build_city_df(df, "Abilene, Texas, US", False)