这里有我的 Python 代码，我不明白为什么我会收到以下错误。任何指导或帮助将不胜感激。
UnboundLocalError：赋值前引用的局部变量"top_performer">
def create(X， y， **kwargs(：
method = kwargs.get("method", None)
#method = kwargs.get("method", "Binary_operators")
#method = kwargs.get("method", "Binning")
#method = kwargs.pop("method", "Cluster")
#categorical_cols = [c for c, t in zip(X.columns, X_column_types) if t in [DATATYPE_CATEGORY_INT, DATATYPE_CATEGORY_STRING]]
#numerical_cols = [c for c, t in zip(X.columns, X_column_types) if t == DATATYPE_NUMBER]
#categorical = X[categorical_cols]
#numerical = X[numerical_cols]
categorical = X.select_dtypes(include=[object])
numerical = X.select_dtypes(exclude=[object])
# feature selection using Genetic Algorithm
if method == "fs_GA":
print("fs_GA")
enc = OneHotEncoder()
enc.fit(categorical)
Data_cat=pd.DataFrame(enc.transform(categorical).toarray())
X_data = pd.concat([numerical, Data_cat], axis=1)
if y.dtype == int:
y = y
else:
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
le.fit(y)
y = le.transform(y)
X_train, X_test, y_train, y_test = train_test_split(X_data, y, train_size=0.8, random_state=42)
def get_fitness(individual):
if y.dtype == int:
rg = RandomForestRegressor(random_state=42)
else:
rg = RandomForestClassifier(random_state=42)
columns = [column for (column, binary_value) in zip(X_train.columns, individual) if binary_value]
training_set = X_train[columns]
test_set = X_test[columns]
rg.fit(training_set.values, y_train)
preds = rg.predict(test_set.values)
return 100 / np.sqrt(mean_squared_error(y_test, preds))
individual = [1] * 100
get_fitness(individual)
def get_population_fitness(population):
return sorted([(individual, get_fitness(individual)) for individual in population], key=lambda tup: tup[1], reverse=True)
def crossover(individual_a, individual_b):
crossing_point = random.randint(0, 99)
offspring_a = individual_a[0:crossing_point] + individual_b[crossing_point:100]
offspring_b = individual_b[0:crossing_point] + individual_a[crossing_point:100]
return offspring_a, offspring_b
def tournament(current_population):
index = sorted(random.sample(range(0, 20), 5))
tournament_members = [current_population[i] for i in index]
total_fitness = sum([individual[1] for individual in tournament_members])
probabilities = [individual[1] / total_fitness for individual in tournament_members]
index_a, index_b = np.random.choice(5, size=2, p=probabilities)
return crossover(tournament_members[index_a][0], tournament_members[index_b][0])
def mutation(individual):
mutation_point = random.randint(0, 99)
if(individual[mutation_point]):
individual[mutation_point] = 0
else:
individual[mutation_point] = 1
def build_next_generation(current_population, mutation_rate):
next_generation = []
next_generation.append(current_population[0][0]) # elitism
next_generation.append(current_population[random.randint(1,19)][0]) # randomness
for i in range(9): # tournaments
offspring_a, offspring_b = tournament(current_population)
next_generation.append(offspring_a)
next_generation.append(offspring_b)
for individual in next_generation: # mutation
if(random.randint(1,mutation_rate) == 1):
mutation(individual)
return next_generation
def run_ga(current_population, num_of_generations, mutation_rate=1000):
fittest_individuals = []
for i in range(num_of_generations):
current_population = get_population_fitness(current_population) # get pop fitness
fittest_individuals.append(current_population[0]) # record fittest individual (for graphing and analysis)
current_population = build_next_generation(current_population, mutation_rate) # make new population
return fittest_individuals
initial_population = [[random.randint(0, 1) for i in range(100)] for i in range(20)]
high_mutation_fittest = run_ga(initial_population, 100, mutation_rate=5)
high_mutation_fitness = [ind[1] for ind in high_mutation_fittest]
for item in high_mutation_fittest[:-1]:
if item[1] == max(high_mutation_fitness):
top_performer = item
break
print("Total features included: " + str(top_performer[0].count(1)))
selected_features = [column for (column, binary_value) in zip(X.columns, top_performer[0]) if binary_value]
excluded_features = [column for (column, binary_value) in zip(X.columns, top_performer[0]) if not binary_value]
X = X[selected_features]
if method == "Binary_operators":
print("binaryoperators")
if method == "Binning":
print("binning")
else:
print("Discretization")
if method == "Cluster":
print("clustering")
else:
print("no-cluster")
print("normal_autocross")
因此，当我运行代码时，出现以下错误，我似乎不明白这意味着什么。有人可以向我解释为什么我会收到此错误吗？
create(X, y, method="fs_GA")
fs_GA
UnboundLocalError Traceback(最近一次调用( 在 ----> 1 create(X， y， method="fs_GA"(
in create(X， y， **kwargs( 107 top_performer = 项目 108 休息 --> 109 打印("包含的总功能： " + str(top_performer[0].count(1((( 110 111 selected_features = [如果binary_value，则 zip (X.columns， top_performer[0]( 中的 (列， binary_value( 列]
UnboundLocalError：赋值前引用的局部变量"top_performer">
top_performer = 0
for item in high_mutation_fittest[:-1]:
if item[1] == max(high_mutation_fitness):
top_performer = item
break
print("Total features included: " + str(top_performer[0].count(1)))
根据您的代码top_performer是一个 int 变量，而不是数组，str(top_performer)是正确的使用方式。str(top_performer).count('1')，这可能是您正在寻找的。count用于字符串而不是 int