def r_cal(self, df, lon, lat, r):
h_goal = encode(lat, lon, 4)
df1 = df[df.h4 == h_goal[0:4]]
df1 = df1.reset_index(drop=True)
if (self.find_largest(df1, lon, lat, r) < r):
df1 = df[df.h3 == h_goal[0:3]]
df1 = df1.reset_index(drop=True)
if (self.find_largest(df1, lon, lat, r) < r):
df1 = df[df.h2 == h_goal[0:2]]
df1 = df1.reset_index(drop=True)
if (self.find_largest(df1, lon, lat, r) < r):
df1 = df[df.h1 == h_goal[0]]
df1 = df1.reset_index(drop=True)
if (self.find_largest(df1, lon, lat, r) < r):
df1 = df.copy()
self.find_largest(df1, lon, lat, r)
else:
df1 = df1
else:
df1 = df1
else:
df1 = df1
else:
df1 = df1
df_r = df1[df1.distance < r]
return df_r
def preprocessing(df):
h4 = []
h3 = []
h2 = []
h1 = []
for index in range(df.shape[0]):
h = encode(df['lat'][index], df['lon'][index], 4)
h4.append(h)
h3.append(h[0:3])
h2.append(h[0:2])
h1.append(h[0])
df.insert(0, 'h4', h4)
df.insert(0, 'h3', h3)
df.insert(0, 'h2', h2)
df.insert(0, 'h1', h1)
return df
def topk(self, df, lon, lat, k):
h_goal = encode(lat, lon, 4)
df1 = df
if df1[df1.h1 == h_goal[00000]].shape[0] > k:
df1 = df1[df1.h1 == h_goal[0]]
if df1[df1.h2 == h_goal[0:2]].shape[0] > k:
df1 = df1[df1.h2 == h_goal[0:2]]
if df1[df1.h3 == h_goal[0:3]].shape[0] > k:
df1 = df1[df1.h3 == h_goal[0:3]]
if df1[df1.h4 == h_goal[0:4]].shape[0] > k:
df1 = df1[df1.h4 == h_goal[0:4]]
df1 = df1.reset_index(drop=True)
df_res = self.k_cal(df1, lon, lat, k)
return df_res
def update_and_transform(self, data_type):
refined_data = []
for item in self.data_dict:
lat = item['latitude']
lng = item['longitude']
tz = item['timezone']
if data_type in ['alerts', 'ALERTS', 'Alerts', 'alert', 'ALERT']:
data = item.get('alerts')
elif data_type in ['hourly', 'Hourly', 'HOURLY']:
data = item['hourly'].get('data')
elif data_type in ['daily', 'DAILY', 'Daily']:
data = item['daily'].get('data')
else:
raise Exception('Unrecognized data section passed')
try:
for v in data:
v.update({'latitude': lat, 'longitude': lng, 'tzone': tz})
except:
continue
refined_data.append(data)
df_list = [pd.DataFrame(item) for item in refined_data if item]
if not df_list:
return pd.DataFrame()
df = pd.concat(df_list).reset_index(drop=True)
df['id'] = [uuid.uuid4() for _ in range(len(df.index))]
if 'precipType' and 'precipAccumulation' in df.columns:
df = self.null_handler(df)
time_cols = [
col for col in df.columns
if 'time' in col.lower() or 'expires' in col.lower()
]
for col in time_cols:
df[col] = df.apply(lambda x: pd.Timestamp(
x[col], unit='s', tz=x['tzone']).tz_convert(tz='UTC'),
axis=1)
df['geohash'] = df.apply(
lambda x: encode(x['latitude'], x['longitude']), axis=1)
return df
"""
# convert decimal degrees to radians
lon1, lat1, lon2, lat2 = map(radians, [lon1, lat1, lon2, lat2])
# haversine formula
dlon = lon2 - lon1
dlat = lat2 - lat1
a = sin(dlat/2)**2 + cos(lat1) * cos(lat2) * sin(dlon/2)**2
c = 2 * asin(sqrt(a))
r = 6371 # Radius of earth in kilometers. Use 3956 for miles
return c * r
if len(argv) == 3:
lat,lon = float(argv[1]), float(argv[2])
# print(lat, lon, Geohash.encode(lat, lon))
print(lat, lon, encode(lat, lon))
else:
for k,v in th.items():
lat,lon = v[0],v[1]
# print(k, encode(lat, lon), lat, lon)
encoded = encode(lat, lon)
th[k] = (encoded, encoded[:8],v)
for k,v in th.items():
print(k,v, len(v[0]))
for k,v in th.items():
pass
for a,b in comb(th.items(),2):
n1, n2, c1, c2 = a[0], b[0], a[1][2],b[1][2]
# print(a[1][2],b[1][2])
lat1,lon1 = c1