def main(input_path="ubicaciones.csv",
balance_deviations=[0.1, 0.15, 0.2, 0.3]):
"""
Use different balance deviations to test complex lp function to minimize.
Args:
input_path : csv path with information regarding agencies, frequency, volume and coordinates
balance_deviations = list with percentage of deviations, for calaculation refer to stops_gap and items_gap
Returns:
None
"""
df = pd.read_csv(input_path)
df.loc[df[df["Vol_Entrega"] == 0].index, "Vol_Entrega"] = 1
zones = ["D1", "D2", "D3", "D4", "D5", "D6"]
agencies = list("A" + df["Id_Cliente"].astype(str))
vol_delivery = list(df["Vol_Entrega"])
vol_stores = list(df["Vol_Entrega"] * df["Frecuencia"])
frequency = list(df["Frecuencia"])
stores_volume = dict(zip(agencies, vol_stores))
stores_frequency = dict(zip(agencies, frequency))
vol_delivery = dict(zip(agencies, vol_delivery))
scaler = MinMaxScaler()
fitted_scaler = scaler.fit(df[["lat", "lon"]])
scaled_coordinates = fitted_scaler.transform(df[["lat", "lon"]])
kmeans = KMeansConstrained(n_clusters=6,
size_min=604,
size_max=605,
random_state=12,
n_init=100,
max_iter=200,
n_jobs=-1)
kmeans_values = kmeans.fit(scaled_coordinates)
df["kmeans"] = list(kmeans.predict(scaled_coordinates))
vectorized_lat_lon = df[["lat", "lon"]].to_numpy()
cluster_centers = fitted_scaler.inverse_transform(kmeans.cluster_centers_)
distance_matrix = cdist(cluster_centers,
vectorized_lat_lon,
metric="cityblock")
routes = [(z, a) for z in zones for a in agencies]
distances = pulp.makeDict([zones, agencies], distance_matrix, 0)
flow = pulp.LpVariable.dicts("Distribution", (zones, agencies), 0, None)
using = pulp.LpVariable.dicts("BelongstoZone", (zones, agencies), 0, 1,
pulp.LpInteger)
for percentage in balance_deviations:
prob = pulp.LpProblem("BrewingDataCup2020_" + str(percentage),
pulp.LpMinimize)
prob += pulp.lpSum([
distances[z][a] * flow[z][a] for (z, a) in routes
]) + pulp.lpSum([distances[z][a] * using[z][a]
for (z, a) in routes]), "totalCosts"
stops_upper, stops_lower = stops_gap(percentage)
distr_upper, distr_lower = items_gap(percentage)
for z in zones:
prob += pulp.lpSum([using[z][a] for a in agencies
]) <= stops_upper, "SumStopsInZoneUpper %s" % z
prob += pulp.lpSum([using[z][a] for a in agencies
]) >= stops_lower, "SumStopsInZoneLower %s" % z
prob += pulp.lpSum([flow[z][a] for a in agencies
]) <= distr_upper, "SumDistrInZoneUpper %s" % z
prob += pulp.lpSum([flow[z][a] for a in agencies
]) >= distr_lower, "SumDistrInZoneLower %s" % z
for z in zones:
for a in agencies:
prob += flow[z][a] - (100000 * using[z][a]) <= 0
prob += flow[z][a] <= vol_delivery[a]
for a in agencies:
prob += pulp.lpSum([flow[z][a] for z in zones
]) >= stores_volume[a], "Distribution %s" % a
prob += pulp.lpSum([
using[z][a] for z in zones
]) == stores_frequency[a], "FrequencyDistribution %s" % a
prob.writeLP("lp_files/milp_brewing_" + str(percentage) + ".lp")
solver = pulp.CPLEX_CMD(path=path_to_cplex)
prob.solve(solver)
print("Estado: ", pulp.LpStatus[prob.status])
print("Total Cost: ", pulp.value(prob.objective))
final_df = pd.DataFrame(columns=["D1", "D2", "D3", "D4", "D5", "D6"],
index=(range(1, 3626)))
final_distr = dict()
for v in prob.variables():
if (v.name).find("BelongstoZone_") == 0:
if v.varValue > 0:
dist = v.name[14:]
zone = dist[:2]
id_cliente = int(dist[4:])
final_df.loc[id_cliente, zone] = 1
final_df.fillna(0, inplace=True)
final_df = final_df.astype(int).reset_index().rename(
columns={"index": "Id_Cliente"})
final_df.to_csv("lp_solutions/cplex_opt_" + str(percentage) + "_" +
str(pulp.value(prob.objective)) + ".csv",
header=True,
index=False)
def test_float_precision():
km = KMeansConstrained(n_init=1, random_state=30)
inertia = {}
X_new = {}
centers = {}
for dtype in [np.float64, np.float32]:
X_test = X.astype(dtype)
km.fit(X_test)
# dtype of cluster centers has to be the dtype of the input
# data
assert_equal(km.cluster_centers_.dtype, dtype)
inertia[dtype] = km.inertia_
X_new[dtype] = km.transform(X_test)
centers[dtype] = km.cluster_centers_
# ensure the extracted row is a 2d array
assert_equal(km.predict(X_test[:1]),
km.labels_[0])
if hasattr(km, 'partial_fit'):
km.partial_fit(X_test[0:3])
# dtype of cluster centers has to stay the same after
# partial_fit
assert_equal(km.cluster_centers_.dtype, dtype)
# compare arrays with low precision since the difference between
# 32 and 64 bit sometimes makes a difference up to the 4th decimal
# place
assert_array_almost_equal(inertia[np.float32], inertia[np.float64],
decimal=4)
assert_array_almost_equal(X_new[np.float32], X_new[np.float64],
decimal=4)
assert_array_almost_equal(centers[np.float32], centers[np.float64],
decimal=4)
def test_predict():
km = KMeansConstrained(n_clusters=n_clusters, random_state=42)
km.fit(X)
# sanity check: predict centroid labels
pred = km.predict(km.cluster_centers_)
assert_array_equal(pred, np.arange(n_clusters))
# sanity check: re-predict labeling for training set samples
pred = km.predict(X)
assert_array_equal(pred, km.labels_)
# re-predict labels for training set using fit_predict
pred = km.fit_predict(X)
assert_array_equal(pred, km.labels_)
from k_means_constrained import KMeansConstrained
df=pd.read_csv("https://raw.githubusercontent.com/JavierLilly/Proyecto_Eco/main/BDC_DATA.csv")
#Estandarizando las coordenadas
data= df[['lat','lon']].values.astype('float32',copy=False)
scaler = StandardScaler().fit(data)
data_scal = scaler.transform(data)
df_ = df
df_[['lat','lon']]=data_scal
#Construyendo el modelo de clustering min - max size
coor = df_[['lat','lon']]
model = KMeansConstrained(n_clusters=6,size_min=600,size_max=700,random_state=5565280).fit(coor)
y = model.predict(coor) # Predicion
df_['cluster'] = y
#Gráfica Todos con Frecuencia >=1
cdict={0:'red',1:'black',2:'yellow',3:'green',4:'blue',5:'grey'}
plt.figure(figsize=(10,10))
sns.set()
for g in np.unique(y):
plt.scatter(coor['lat'][y==g], coor['lon'][y==g], c = cdict[g], label = g, s = 60)
# plt.scatter(df['lat'][df['Frecuencia']==2],df['lon'][df['Frecuencia']==2],c='purple',s=80,alpha = .5)
# plt.scatter(df['lat'][df['Frecuencia']==3],df['lon'][df['Frecuencia']==3],c='brown',s=150,)
plt.legend()
#Reducimos los datos
# -*- coding: utf-8 -*- """ Created on Sat Oct 17 19:13:48 2020 @author: lcota """ from k_means_constrained import KMeansConstrained clf = KMeansConstrained(n_clusters=2, size_min=2, size_max=5, random_state=0) clf.fit(X) clf.cluster_centers_ clf.predict([[0, 0], [4, 4]])
