def transform(self, X, y=None):
nyc_center = (40.7141667, -74.0063889)
X["nyc_lat"], X["nyc_lng"] = nyc_center[0], nyc_center[1]
args_pickup = dict(start_lat="nyc_lat", start_lon="nyc_lng",
end_lat="pickup_latitude", end_lon="pickup_longitude")
args_dropoff = dict(start_lat="nyc_lat", start_lon="nyc_lng",
end_lat="dropoff_latitude", end_lon="dropoff_longitude")
X['pickup_distance_to_center'] = haversine_vectorized(X, **args_pickup)
X['dropoff_distance_to_center'] = haversine_vectorized(X, **args_dropoff)
return X[["pickup_distance_to_center", "dropoff_distance_to_center"]]
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
return pd.DataFrame(haversine_vectorized(X,
start_lat=self.start_lat,
start_lon=self.start_lon,
end_lat=self.end_lat,
end_lon=self.end_lon))
def transform(self, X, y=None):
assert isinstance(X, pd.DataFrame)
if self.distance_type == "haversine":
X["distance"] = haversine_vectorized(X, **dist_args)
if self.distance_type == "euclidian":
X["distance"] = minkowski_distance()
return X[["distance"]]
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
X['distance'] = haversine_vectorized(X,
start_lat="pickup_latitude",
start_lon="pickup_longitude",
end_lat="dropoff_latitude",
end_lon="dropoff_longitude")
return X[['distance']]
def transform(self, X, y=None):
assert isinstance(X, pd.DataFrame)
if self.distance_type == "haversine":
X["distance"] = haversine_vectorized(X, **DIST_ARGS)
if self.distance_type == "euclidian":
X["distance"] = minkowski_distance(X, p=2, **DIST_ARGS)
if self.distance_type == "manhattan":
X["distance"] = minkowski_distance(X, p=1, **DIST_ARGS)
return X[["distance"]]
def transform(self, X, y=None):
assert isinstance(X, pd.DataFrame)
X_ = X.copy()
X_["distance"] = haversine_vectorized(X_,
start_lat=self.start_lat,
start_lon=self.start_lon,
end_lat=self.end_lat,
end_lon=self.end_lon)
return X_[['distance']]
def transform(self, X, y=None):
jfk_center = (40.6441666667, -73.7822222222)
X["jfk_lat"], X["jfk_lng"] = jfk_center[0], jfk_center[1]
args_pickup = dict(start_lat="jfk_lat",
start_lon="jfk_lng",
end_lat="pickup_latitude",
end_lon="pickup_longitude")
args_dropoff = dict(start_lat="jfk_lat",
start_lon="jfk_lng",
end_lat="dropoff_latitude",
end_lon="dropoff_longitude")
X['pickup_distance_to_jfk'] = haversine_vectorized(X, **args_pickup)
X['dropoff_distance_to_jfk'] = haversine_vectorized(X, **args_dropoff)
X['from_to_airport'] = (np.logical_or(X['pickup_distance_to_jfk']<2,\
X['dropoff_distance_to_jfk']<2))*1
#return X[["pickup_distance_to_center", "dropoff_distance_to_center",'from_to_airport']]
return X[['from_to_airport']]
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance_to_center'"""
nyc_center = (40.7141667, -74.0063889)
X["nyc_latitude"], X["nyc_longitude"] = nyc_center[0], nyc_center[1]
args = dict(start_lat="nyc_latitude",
start_lon="nyc_longitude",
end_lat="pickup_latitude",
end_lon="pickup_longitude")
X['distance_to_center'] = haversine_vectorized(X, **args)
return X[['distance_to_center']]
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
assert isinstance(X, pd.DataFrame)
X_temp = X.copy()
X_temp['distance'] = haversine_vectorized(X_temp,
start_lat=self.start_lat,
start_lon=self.start_lon,
end_lat=self.end_lat,
end_lon=self.end_lon)
return X_temp[['distance']]
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
X['distance'] = haversine_vectorized(X,
start_lat=self.start_lat,
start_lon=self.start_lon,
end_lat=self.end_lat,
end_lon=self.end_lon)
X = X.reset_index(drop=True)
return X[['distance']]
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
assert isinstance(X, pd.DataFrame)
X_temp = X.copy()
X_temp['nyc_lat'] = 40.7141667
X_temp['nyc_lon'] = -74.0063889
X_temp['distance_to_center'] = haversine_vectorized(
X_temp,
start_lat=self.nyc_lat,
start_lon=self.nyc_lon,
end_lat=self.end_lat,
end_lon=self.end_lon)
return X_temp[['distance_to_center']]
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
return pd.DataFrame(haversine_vectorized (X.copy(),self.start_lat,self.start_lon,self.end_lat,self.end_lon))\
.rename(columns={0:"distance"})
def transform(self, X, y=None):
a = haversine_vectorized(X)
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
return pd.DataFrame(a)
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only 1 column: 'distance'"""
df = pd.DataFrame(haversine_vectorized(X.copy()))
df.columns = ['distance']
return df
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
assert isinstance(X,pd.DataFrame)
X_ = X.copy()
X_['distance'] = haversine_vectorized(X_)
return X_[['distance']]
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
return pd.DataFrame(haversine_vectorized(X.copy()),columns=['distance']) \
.sort_index()
def transform(self, X, y=None):
return pd.DataFrame(haversine_vectorized(X))
def test_haversine():
df = get_data(nrows=1)
assert round(haversine_vectorized(df)[0], 2) == 1.03, "Distance not right"
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
X_ = X.copy()
X_["distance"] = haversine_vectorized(X_)
distance = pd.DataFrame(X_["distance"])
return distance
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
X = X.copy()
X['distance'] = haversine_vectorized(X)
return X[['distance']]
def transform(self, X, y=None):
"""Returns a copy of the DataFrame X with only one column: 'distance'"""
a = pd.DataFrame()
a['distance'] = haversine_vectorized(X)
return a
