如何从 GridSearchCV 绘制网格分数？
How to graph grid scores from GridSearchCV?
我正在寻找一种在 sklearn 中从 GridSearchCV 绘制 grid_scores_ 图形的方法。在这个例子中，我试图通过网格搜索为 SVR 算法寻找最佳伽玛和 C 参数。我的代码如下所示：
C_range = 10.0 ** np.arange(-4, 4)
gamma_range = 10.0 ** np.arange(-4, 4)
param_grid = dict(gamma=gamma_range.tolist(), C=C_range.tolist())
grid = GridSearchCV(SVR(kernel='rbf', gamma=0.1),param_grid, cv=5)
grid.fit(X_train,y_train)
print(grid.grid_scores_)
在我 运行 代码并打印网格分数后，我得到以下结果：
[mean: -3.28593, std: 1.69134, params: {'gamma': 0.0001, 'C': 0.0001}, mean: -3.29370, std: 1.69346, params: {'gamma': 0.001, 'C': 0.0001}, mean: -3.28933, std: 1.69104, params: {'gamma': 0.01, 'C': 0.0001}, mean: -3.28925, std: 1.69106, params: {'gamma': 0.1, 'C': 0.0001}, mean: -3.28925, std: 1.69106, params: {'gamma': 1.0, 'C': 0.0001}, mean: -3.28925, std: 1.69106, params: {'gamma': 10.0, 'C': 0.0001},etc]
我想根据 gamma 和 C 参数可视化所有分数（平均值）。我试图获得的图表应该如下所示：
其中x轴是gamma，y轴是平均得分（在本例中为均方根误差），不同的线代表不同的C值。
from sklearn.svm import SVC
from sklearn.grid_search import GridSearchCV
from sklearn import datasets
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
digits = datasets.load_digits()
X = digits.data
y = digits.target
clf_ = SVC(kernel='rbf')
Cs = [1, 10, 100, 1000]
Gammas = [1e-3, 1e-4]
clf = GridSearchCV(clf_,
dict(C=Cs,
gamma=Gammas),
cv=2,
pre_dispatch='1*n_jobs',
n_jobs=1)
clf.fit(X, y)
scores = [x[1] for x in clf.grid_scores_]
scores = np.array(scores).reshape(len(Cs), len(Gammas))
for ind, i in enumerate(Cs):
plt.plot(Gammas, scores[ind], label='C: ' + str(i))
plt.legend()
plt.xlabel('Gamma')
plt.ylabel('Mean score')
plt.show()
- 代码基于 this.
- 唯一令人费解的部分：sklearn 将始终遵守 C 和 Gamma 的顺序 -> 官方示例使用此 "ordering"
输出：
遍历参数网格的顺序是确定的，因此可以直接对其进行整形和绘制。像这样：
scores = [entry.mean_validation_score for entry in grid.grid_scores_]
# the shape is according to the alphabetical order of the parameters in the grid
scores = np.array(scores).reshape(len(C_range), len(gamma_range))
for c_scores in scores:
plt.plot(gamma_range, c_scores, '-')
@sascha 显示的代码是正确的。但是，grid_scores_ 属性将很快被弃用。最好使用 cv_results 属性。
它可以以与@sascha 方法类似的方式实现：
def plot_grid_search(cv_results, grid_param_1, grid_param_2, name_param_1, name_param_2):
# Get Test Scores Mean and std for each grid search
scores_mean = cv_results['mean_test_score']
scores_mean = np.array(scores_mean).reshape(len(grid_param_2),len(grid_param_1))
scores_sd = cv_results['std_test_score']
scores_sd = np.array(scores_sd).reshape(len(grid_param_2),len(grid_param_1))
# Plot Grid search scores
_, ax = plt.subplots(1,1)
# Param1 is the X-axis, Param 2 is represented as a different curve (color line)
for idx, val in enumerate(grid_param_2):
ax.plot(grid_param_1, scores_mean[idx,:], '-o', label= name_param_2 + ': ' + str(val))
ax.set_title("Grid Search Scores", fontsize=20, fontweight='bold')
ax.set_xlabel(name_param_1, fontsize=16)
ax.set_ylabel('CV Average Score', fontsize=16)
ax.legend(loc="best", fontsize=15)
ax.grid('on')
# Calling Method
plot_grid_search(pipe_grid.cv_results_, n_estimators, max_features, 'N Estimators', 'Max Features')
以上结果如下图：
我想做类似的事情（但可扩展到大量参数），这是我生成输出群图的解决方案：
score = pd.DataFrame(gs_clf.grid_scores_).sort_values(by='mean_validation_score', ascending = False)
for i in parameters.keys():
print(i, len(parameters[i]), parameters[i])
score[i] = score.parameters.apply(lambda x: x[i])
l =['mean_validation_score'] + list(parameters.keys())
for i in list(parameters.keys()):
sns.swarmplot(data = score[l], x = i, y = 'mean_validation_score')
#plt.savefig('170705_sgd_optimisation//'+i+'.jpg', dpi = 100)
plt.show()
这是一个利用 seaborn pointplot 的解决方案。这种方法的优点是它允许您在搜索超过 2 个参数时绘制结果
import seaborn as sns
import pandas as pd
def plot_cv_results(cv_results, param_x, param_z, metric='mean_test_score'):
"""
cv_results - cv_results_ attribute of a GridSearchCV instance (or similar)
param_x - name of grid search parameter to plot on x axis
param_z - name of grid search parameter to plot by line color
"""
cv_results = pd.DataFrame(cv_results)
col_x = 'param_' + param_x
col_z = 'param_' + param_z
fig, ax = plt.subplots(1, 1, figsize=(11, 8))
sns.pointplot(x=col_x, y=metric, hue=col_z, data=cv_results, ci=99, n_boot=64, ax=ax)
ax.set_title("CV Grid Search Results")
ax.set_xlabel(param_x)
ax.set_ylabel(metric)
ax.legend(title=param_z)
return fig
使用 xgboost 的示例：
from xgboost import XGBRegressor
from sklearn import GridSearchCV
params = {
'max_depth': [3, 6, 9, 12],
'gamma': [0, 1, 10, 20, 100],
'min_child_weight': [1, 4, 16, 64, 256],
}
model = XGBRegressor()
grid = GridSearchCV(model, params, scoring='neg_mean_squared_error')
grid.fit(...)
fig = plot_cv_results(grid.cv_results_, 'gamma', 'min_child_weight')
这将生成一个图形，在 x 轴上显示 gamma 正则化参数，在线条颜色中显示 min_child_weight 正则化参数，以及任何其他网格搜索参数（在本例中 max_depth) 将通过 seaborn 点图的 99% 置信区间的分布来描述。
*请注意，在下面的示例中，我对上面的代码稍作了改动。
当我试图绘制平均分数与否时，这对我有用。随机森林中的树木。 reshape() 函数有助于找出平均值。
param_n_estimators = cv_results['param_n_estimators']
param_n_estimators = np.array(param_n_estimators)
mean_n_estimators = np.mean(param_n_estimators.reshape(-1,5), axis=0)
mean_test_scores = cv_results['mean_test_score']
mean_test_scores = np.array(mean_test_scores)
mean_test_scores = np.mean(mean_test_scores.reshape(-1,5), axis=0)
mean_train_scores = cv_results['mean_train_score']
mean_train_scores = np.array(mean_train_scores)
mean_train_scores = np.mean(mean_train_scores.reshape(-1,5), axis=0)
为了在调整多个超参数时绘制结果，我所做的是将所有参数固定为最佳值，一个除外，并绘制另一个参数的每个值的平均分。
def plot_search_results(grid):
"""
Params:
grid: A trained GridSearchCV object.
"""
## Results from grid search
results = grid.cv_results_
means_test = results['mean_test_score']
stds_test = results['std_test_score']
means_train = results['mean_train_score']
stds_train = results['std_train_score']
## Getting indexes of values per hyper-parameter
masks=[]
masks_names= list(grid.best_params_.keys())
for p_k, p_v in grid.best_params_.items():
masks.append(list(results['param_'+p_k].data==p_v))
params=grid.param_grid
## Ploting results
fig, ax = plt.subplots(1,len(params),sharex='none', sharey='all',figsize=(20,5))
fig.suptitle('Score per parameter')
fig.text(0.04, 0.5, 'MEAN SCORE', va='center', rotation='vertical')
pram_preformace_in_best = {}
for i, p in enumerate(masks_names):
m = np.stack(masks[:i] + masks[i+1:])
pram_preformace_in_best
best_parms_mask = m.all(axis=0)
best_index = np.where(best_parms_mask)[0]
x = np.array(params[p])
y_1 = np.array(means_test[best_index])
e_1 = np.array(stds_test[best_index])
y_2 = np.array(means_train[best_index])
e_2 = np.array(stds_train[best_index])
ax[i].errorbar(x, y_1, e_1, linestyle='--', marker='o', label='test')
ax[i].errorbar(x, y_2, e_2, linestyle='-', marker='^',label='train' )
ax[i].set_xlabel(p.upper())
plt.legend()
plt.show()
我在具有不同学习率、最大深度和估计器数量的 xgboost 上使用网格搜索。
gs_param_grid = {'max_depth': [3,4,5],
'n_estimators' : [x for x in range(3000,5000,250)],
'learning_rate':[0.01,0.03,0.1]
}
gbm = XGBRegressor()
grid_gbm = GridSearchCV(estimator=gbm,
param_grid=gs_param_grid,
scoring='neg_mean_squared_error',
cv=4,
verbose=1
)
grid_gbm.fit(X_train,y_train)
为了创建误差与具有不同学习率的估计器数量的图表，我使用了以下方法：
y=[]
cvres = grid_gbm.cv_results_
best_md=grid_gbm.best_params_['max_depth']
la=gs_param_grid['learning_rate']
n_estimators=gs_param_grid['n_estimators']
for mean_score, params in zip(cvres["mean_test_score"], cvres["params"]):
if params["max_depth"]==best_md:
y.append(np.sqrt(-mean_score))
y=np.array(y).reshape(len(la),len(n_estimators))
%matplotlib inline
plt.figure(figsize=(8,8))
for y_arr, label in zip(y, la):
plt.plot(n_estimators, y_arr, label=label)
plt.title('Error for different learning rates(keeping max_depth=%d(best_param))'%best_md)
plt.legend()
plt.xlabel('n_estimators')
plt.ylabel('Error')
plt.show()
剧情可以看这里：
请注意，可以类似地为误差与具有不同最大深度（或根据用户情况的任何其他参数）的估计器数量创建图表。
这是可以生成绘图的完整工作代码，因此您可以使用 GridSearchCV 完全可视化最多 3 个参数的变化。这是 运行 代码时您将看到的内容：
- 参数1（x轴）
- 交叉验证平均得分（y 轴）
- Parameter2（为每个不同的 Parameter2 值绘制的额外线条，带有供参考的图例）
- Parameter3（每个不同的Parameter3值都会弹出额外的图表，让您查看这些不同图表之间的差异）
对于绘制的每条线，还显示了您可以根据您 运行 的多个 CV 预期交叉验证平均得分的标准偏差。享受吧！
from sklearn import tree
from sklearn import model_selection
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.datasets import load_digits
digits = load_digits()
X, y = digits.data, digits.target
Algo = [['DecisionTreeClassifier', tree.DecisionTreeClassifier(), # algorithm
'max_depth', [1, 2, 4, 6, 8, 10, 12, 14, 18, 20, 22, 24, 26, 28, 30], # Parameter1
'max_features', ['sqrt', 'log2', None], # Parameter2
'criterion', ['gini', 'entropy']]] # Parameter3
def plot_grid_search(cv_results, grid_param_1, grid_param_2, name_param_1, name_param_2, title):
# Get Test Scores Mean and std for each grid search
grid_param_1 = list(str(e) for e in grid_param_1)
grid_param_2 = list(str(e) for e in grid_param_2)
scores_mean = cv_results['mean_test_score']
scores_std = cv_results['std_test_score']
params_set = cv_results['params']
scores_organized = {}
std_organized = {}
std_upper = {}
std_lower = {}
for p2 in grid_param_2:
scores_organized[p2] = []
std_organized[p2] = []
std_upper[p2] = []
std_lower[p2] = []
for p1 in grid_param_1:
for i in range(len(params_set)):
if str(params_set[i][name_param_1]) == str(p1) and str(params_set[i][name_param_2]) == str(p2):
mean = scores_mean[i]
std = scores_std[i]
scores_organized[p2].append(mean)
std_organized[p2].append(std)
std_upper[p2].append(mean + std)
std_lower[p2].append(mean - std)
_, ax = plt.subplots(1, 1)
# Param1 is the X-axis, Param 2 is represented as a different curve (color line)
# plot means
for key in scores_organized.keys():
ax.plot(grid_param_1, scores_organized[key], '-o', label= name_param_2 + ': ' + str(key))
ax.fill_between(grid_param_1, std_lower[key], std_upper[key], alpha=0.1)
ax.set_title(title)
ax.set_xlabel(name_param_1)
ax.set_ylabel('CV Average Score')
ax.legend(loc="best")
ax.grid('on')
plt.show()
dataset = 'Titanic'
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
cv_split = model_selection.KFold(n_splits=10, random_state=2)
for i in range(len(Algo)):
name = Algo[0][0]
alg = Algo[0][1]
param_1_name = Algo[0][2]
param_1_range = Algo[0][3]
param_2_name = Algo[0][4]
param_2_range = Algo[0][5]
param_3_name = Algo[0][6]
param_3_range = Algo[0][7]
for p in param_3_range:
# grid search
param = {
param_1_name: param_1_range,
param_2_name: param_2_range,
param_3_name: [p]
}
grid_test = GridSearchCV(alg, param_grid=param, scoring='accuracy', cv=cv_split)
grid_test.fit(X_train, y_train)
plot_grid_search(grid_test.cv_results_, param[param_1_name], param[param_2_name], param_1_name, param_2_name, dataset + ' GridSearch Scores: ' + name + ', ' + param_3_name + '=' + str(p))
param = {
param_1_name: param_1_range,
param_2_name: param_2_range,
param_3_name: param_3_range
}
grid_final = GridSearchCV(alg, param_grid=param, scoring='accuracy', cv=cv_split)
grid_final.fit(X_train, y_train)
best_params = grid_final.best_params_
alg.set_params(**best_params)
@nathandrake 尝试以下根据@david-alvarez 的代码改编的代码：
def plot_grid_search(cv_results, metric, grid_param_1, grid_param_2, name_param_1, name_param_2):
# Get Test Scores Mean and std for each grid search
scores_mean = cv_results[('mean_test_' + metric)]
scores_sd = cv_results[('std_test_' + metric)]
if grid_param_2 is not None:
scores_mean = np.array(scores_mean).reshape(len(grid_param_2),len(grid_param_1))
scores_sd = np.array(scores_sd).reshape(len(grid_param_2),len(grid_param_1))
# Set plot style
plt.style.use('seaborn')
# Plot Grid search scores
_, ax = plt.subplots(1,1)
if grid_param_2 is not None:
# Param1 is the X-axis, Param 2 is represented as a different curve (color line)
for idx, val in enumerate(grid_param_2):
ax.plot(grid_param_1, scores_mean[idx,:], '-o', label= name_param_2 + ': ' + str(val))
else:
# If only one Param1 is given
ax.plot(grid_param_1, scores_mean, '-o')
ax.set_title("Grid Search", fontsize=20, fontweight='normal')
ax.set_xlabel(name_param_1, fontsize=16)
ax.set_ylabel('CV Average ' + str.capitalize(metric), fontsize=16)
ax.legend(loc="best", fontsize=15)
ax.grid('on')
如您所见，我添加了支持包含多个指标的网格搜索的功能。您只需在调用绘图函数时指定要绘制的指标。
此外，如果您的网格搜索只调整了一个参数，您可以简单地为 grid_param_2 和 name_param_2.
指定 None
调用如下：
plot_grid_search(grid_search.cv_results_,
'Accuracy',
list(np.linspace(0.001, 10, 50)),
['linear', 'rbf'],
'C',
'kernel')
我正在寻找一种在 sklearn 中从 GridSearchCV 绘制 grid_scores_ 图形的方法。在这个例子中，我试图通过网格搜索为 SVR 算法寻找最佳伽玛和 C 参数。我的代码如下所示：
C_range = 10.0 ** np.arange(-4, 4)
gamma_range = 10.0 ** np.arange(-4, 4)
param_grid = dict(gamma=gamma_range.tolist(), C=C_range.tolist())
grid = GridSearchCV(SVR(kernel='rbf', gamma=0.1),param_grid, cv=5)
grid.fit(X_train,y_train)
print(grid.grid_scores_)
在我 运行 代码并打印网格分数后，我得到以下结果：
[mean: -3.28593, std: 1.69134, params: {'gamma': 0.0001, 'C': 0.0001}, mean: -3.29370, std: 1.69346, params: {'gamma': 0.001, 'C': 0.0001}, mean: -3.28933, std: 1.69104, params: {'gamma': 0.01, 'C': 0.0001}, mean: -3.28925, std: 1.69106, params: {'gamma': 0.1, 'C': 0.0001}, mean: -3.28925, std: 1.69106, params: {'gamma': 1.0, 'C': 0.0001}, mean: -3.28925, std: 1.69106, params: {'gamma': 10.0, 'C': 0.0001},etc]
我想根据 gamma 和 C 参数可视化所有分数（平均值）。我试图获得的图表应该如下所示：
其中x轴是gamma，y轴是平均得分（在本例中为均方根误差），不同的线代表不同的C值。
from sklearn.svm import SVC
from sklearn.grid_search import GridSearchCV
from sklearn import datasets
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
digits = datasets.load_digits()
X = digits.data
y = digits.target
clf_ = SVC(kernel='rbf')
Cs = [1, 10, 100, 1000]
Gammas = [1e-3, 1e-4]
clf = GridSearchCV(clf_,
dict(C=Cs,
gamma=Gammas),
cv=2,
pre_dispatch='1*n_jobs',
n_jobs=1)
clf.fit(X, y)
scores = [x[1] for x in clf.grid_scores_]
scores = np.array(scores).reshape(len(Cs), len(Gammas))
for ind, i in enumerate(Cs):
plt.plot(Gammas, scores[ind], label='C: ' + str(i))
plt.legend()
plt.xlabel('Gamma')
plt.ylabel('Mean score')
plt.show()
- 代码基于 this.
- 唯一令人费解的部分：sklearn 将始终遵守 C 和 Gamma 的顺序 -> 官方示例使用此 "ordering"
输出：
遍历参数网格的顺序是确定的，因此可以直接对其进行整形和绘制。像这样：
scores = [entry.mean_validation_score for entry in grid.grid_scores_]
# the shape is according to the alphabetical order of the parameters in the grid
scores = np.array(scores).reshape(len(C_range), len(gamma_range))
for c_scores in scores:
plt.plot(gamma_range, c_scores, '-')
@sascha 显示的代码是正确的。但是，grid_scores_ 属性将很快被弃用。最好使用 cv_results 属性。
它可以以与@sascha 方法类似的方式实现：
def plot_grid_search(cv_results, grid_param_1, grid_param_2, name_param_1, name_param_2):
# Get Test Scores Mean and std for each grid search
scores_mean = cv_results['mean_test_score']
scores_mean = np.array(scores_mean).reshape(len(grid_param_2),len(grid_param_1))
scores_sd = cv_results['std_test_score']
scores_sd = np.array(scores_sd).reshape(len(grid_param_2),len(grid_param_1))
# Plot Grid search scores
_, ax = plt.subplots(1,1)
# Param1 is the X-axis, Param 2 is represented as a different curve (color line)
for idx, val in enumerate(grid_param_2):
ax.plot(grid_param_1, scores_mean[idx,:], '-o', label= name_param_2 + ': ' + str(val))
ax.set_title("Grid Search Scores", fontsize=20, fontweight='bold')
ax.set_xlabel(name_param_1, fontsize=16)
ax.set_ylabel('CV Average Score', fontsize=16)
ax.legend(loc="best", fontsize=15)
ax.grid('on')
# Calling Method
plot_grid_search(pipe_grid.cv_results_, n_estimators, max_features, 'N Estimators', 'Max Features')
以上结果如下图：
我想做类似的事情（但可扩展到大量参数），这是我生成输出群图的解决方案：
score = pd.DataFrame(gs_clf.grid_scores_).sort_values(by='mean_validation_score', ascending = False)
for i in parameters.keys():
print(i, len(parameters[i]), parameters[i])
score[i] = score.parameters.apply(lambda x: x[i])
l =['mean_validation_score'] + list(parameters.keys())
for i in list(parameters.keys()):
sns.swarmplot(data = score[l], x = i, y = 'mean_validation_score')
#plt.savefig('170705_sgd_optimisation//'+i+'.jpg', dpi = 100)
plt.show()
这是一个利用 seaborn pointplot 的解决方案。这种方法的优点是它允许您在搜索超过 2 个参数时绘制结果
import seaborn as sns
import pandas as pd
def plot_cv_results(cv_results, param_x, param_z, metric='mean_test_score'):
"""
cv_results - cv_results_ attribute of a GridSearchCV instance (or similar)
param_x - name of grid search parameter to plot on x axis
param_z - name of grid search parameter to plot by line color
"""
cv_results = pd.DataFrame(cv_results)
col_x = 'param_' + param_x
col_z = 'param_' + param_z
fig, ax = plt.subplots(1, 1, figsize=(11, 8))
sns.pointplot(x=col_x, y=metric, hue=col_z, data=cv_results, ci=99, n_boot=64, ax=ax)
ax.set_title("CV Grid Search Results")
ax.set_xlabel(param_x)
ax.set_ylabel(metric)
ax.legend(title=param_z)
return fig
使用 xgboost 的示例：
from xgboost import XGBRegressor
from sklearn import GridSearchCV
params = {
'max_depth': [3, 6, 9, 12],
'gamma': [0, 1, 10, 20, 100],
'min_child_weight': [1, 4, 16, 64, 256],
}
model = XGBRegressor()
grid = GridSearchCV(model, params, scoring='neg_mean_squared_error')
grid.fit(...)
fig = plot_cv_results(grid.cv_results_, 'gamma', 'min_child_weight')
这将生成一个图形，在 x 轴上显示 gamma 正则化参数，在线条颜色中显示 min_child_weight 正则化参数，以及任何其他网格搜索参数（在本例中 max_depth) 将通过 seaborn 点图的 99% 置信区间的分布来描述。
*请注意，在下面的示例中，我对上面的代码稍作了改动。
当我试图绘制平均分数与否时，这对我有用。随机森林中的树木。 reshape() 函数有助于找出平均值。
param_n_estimators = cv_results['param_n_estimators']
param_n_estimators = np.array(param_n_estimators)
mean_n_estimators = np.mean(param_n_estimators.reshape(-1,5), axis=0)
mean_test_scores = cv_results['mean_test_score']
mean_test_scores = np.array(mean_test_scores)
mean_test_scores = np.mean(mean_test_scores.reshape(-1,5), axis=0)
mean_train_scores = cv_results['mean_train_score']
mean_train_scores = np.array(mean_train_scores)
mean_train_scores = np.mean(mean_train_scores.reshape(-1,5), axis=0)
为了在调整多个超参数时绘制结果，我所做的是将所有参数固定为最佳值，一个除外，并绘制另一个参数的每个值的平均分。
def plot_search_results(grid):
"""
Params:
grid: A trained GridSearchCV object.
"""
## Results from grid search
results = grid.cv_results_
means_test = results['mean_test_score']
stds_test = results['std_test_score']
means_train = results['mean_train_score']
stds_train = results['std_train_score']
## Getting indexes of values per hyper-parameter
masks=[]
masks_names= list(grid.best_params_.keys())
for p_k, p_v in grid.best_params_.items():
masks.append(list(results['param_'+p_k].data==p_v))
params=grid.param_grid
## Ploting results
fig, ax = plt.subplots(1,len(params),sharex='none', sharey='all',figsize=(20,5))
fig.suptitle('Score per parameter')
fig.text(0.04, 0.5, 'MEAN SCORE', va='center', rotation='vertical')
pram_preformace_in_best = {}
for i, p in enumerate(masks_names):
m = np.stack(masks[:i] + masks[i+1:])
pram_preformace_in_best
best_parms_mask = m.all(axis=0)
best_index = np.where(best_parms_mask)[0]
x = np.array(params[p])
y_1 = np.array(means_test[best_index])
e_1 = np.array(stds_test[best_index])
y_2 = np.array(means_train[best_index])
e_2 = np.array(stds_train[best_index])
ax[i].errorbar(x, y_1, e_1, linestyle='--', marker='o', label='test')
ax[i].errorbar(x, y_2, e_2, linestyle='-', marker='^',label='train' )
ax[i].set_xlabel(p.upper())
plt.legend()
plt.show()
我在具有不同学习率、最大深度和估计器数量的 xgboost 上使用网格搜索。
gs_param_grid = {'max_depth': [3,4,5],
'n_estimators' : [x for x in range(3000,5000,250)],
'learning_rate':[0.01,0.03,0.1]
}
gbm = XGBRegressor()
grid_gbm = GridSearchCV(estimator=gbm,
param_grid=gs_param_grid,
scoring='neg_mean_squared_error',
cv=4,
verbose=1
)
grid_gbm.fit(X_train,y_train)
为了创建误差与具有不同学习率的估计器数量的图表，我使用了以下方法：
y=[]
cvres = grid_gbm.cv_results_
best_md=grid_gbm.best_params_['max_depth']
la=gs_param_grid['learning_rate']
n_estimators=gs_param_grid['n_estimators']
for mean_score, params in zip(cvres["mean_test_score"], cvres["params"]):
if params["max_depth"]==best_md:
y.append(np.sqrt(-mean_score))
y=np.array(y).reshape(len(la),len(n_estimators))
%matplotlib inline
plt.figure(figsize=(8,8))
for y_arr, label in zip(y, la):
plt.plot(n_estimators, y_arr, label=label)
plt.title('Error for different learning rates(keeping max_depth=%d(best_param))'%best_md)
plt.legend()
plt.xlabel('n_estimators')
plt.ylabel('Error')
plt.show()
剧情可以看这里：
请注意，可以类似地为误差与具有不同最大深度（或根据用户情况的任何其他参数）的估计器数量创建图表。
这是可以生成绘图的完整工作代码，因此您可以使用 GridSearchCV 完全可视化最多 3 个参数的变化。这是 运行 代码时您将看到的内容：
- 参数1（x轴）
- 交叉验证平均得分（y 轴）
- Parameter2（为每个不同的 Parameter2 值绘制的额外线条，带有供参考的图例）
- Parameter3（每个不同的Parameter3值都会弹出额外的图表，让您查看这些不同图表之间的差异）
对于绘制的每条线，还显示了您可以根据您 运行 的多个 CV 预期交叉验证平均得分的标准偏差。享受吧！
from sklearn import tree
from sklearn import model_selection
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.datasets import load_digits
digits = load_digits()
X, y = digits.data, digits.target
Algo = [['DecisionTreeClassifier', tree.DecisionTreeClassifier(), # algorithm
'max_depth', [1, 2, 4, 6, 8, 10, 12, 14, 18, 20, 22, 24, 26, 28, 30], # Parameter1
'max_features', ['sqrt', 'log2', None], # Parameter2
'criterion', ['gini', 'entropy']]] # Parameter3
def plot_grid_search(cv_results, grid_param_1, grid_param_2, name_param_1, name_param_2, title):
# Get Test Scores Mean and std for each grid search
grid_param_1 = list(str(e) for e in grid_param_1)
grid_param_2 = list(str(e) for e in grid_param_2)
scores_mean = cv_results['mean_test_score']
scores_std = cv_results['std_test_score']
params_set = cv_results['params']
scores_organized = {}
std_organized = {}
std_upper = {}
std_lower = {}
for p2 in grid_param_2:
scores_organized[p2] = []
std_organized[p2] = []
std_upper[p2] = []
std_lower[p2] = []
for p1 in grid_param_1:
for i in range(len(params_set)):
if str(params_set[i][name_param_1]) == str(p1) and str(params_set[i][name_param_2]) == str(p2):
mean = scores_mean[i]
std = scores_std[i]
scores_organized[p2].append(mean)
std_organized[p2].append(std)
std_upper[p2].append(mean + std)
std_lower[p2].append(mean - std)
_, ax = plt.subplots(1, 1)
# Param1 is the X-axis, Param 2 is represented as a different curve (color line)
# plot means
for key in scores_organized.keys():
ax.plot(grid_param_1, scores_organized[key], '-o', label= name_param_2 + ': ' + str(key))
ax.fill_between(grid_param_1, std_lower[key], std_upper[key], alpha=0.1)
ax.set_title(title)
ax.set_xlabel(name_param_1)
ax.set_ylabel('CV Average Score')
ax.legend(loc="best")
ax.grid('on')
plt.show()
dataset = 'Titanic'
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
cv_split = model_selection.KFold(n_splits=10, random_state=2)
for i in range(len(Algo)):
name = Algo[0][0]
alg = Algo[0][1]
param_1_name = Algo[0][2]
param_1_range = Algo[0][3]
param_2_name = Algo[0][4]
param_2_range = Algo[0][5]
param_3_name = Algo[0][6]
param_3_range = Algo[0][7]
for p in param_3_range:
# grid search
param = {
param_1_name: param_1_range,
param_2_name: param_2_range,
param_3_name: [p]
}
grid_test = GridSearchCV(alg, param_grid=param, scoring='accuracy', cv=cv_split)
grid_test.fit(X_train, y_train)
plot_grid_search(grid_test.cv_results_, param[param_1_name], param[param_2_name], param_1_name, param_2_name, dataset + ' GridSearch Scores: ' + name + ', ' + param_3_name + '=' + str(p))
param = {
param_1_name: param_1_range,
param_2_name: param_2_range,
param_3_name: param_3_range
}
grid_final = GridSearchCV(alg, param_grid=param, scoring='accuracy', cv=cv_split)
grid_final.fit(X_train, y_train)
best_params = grid_final.best_params_
alg.set_params(**best_params)
@nathandrake 尝试以下根据@david-alvarez 的代码改编的代码：
def plot_grid_search(cv_results, metric, grid_param_1, grid_param_2, name_param_1, name_param_2):
# Get Test Scores Mean and std for each grid search
scores_mean = cv_results[('mean_test_' + metric)]
scores_sd = cv_results[('std_test_' + metric)]
if grid_param_2 is not None:
scores_mean = np.array(scores_mean).reshape(len(grid_param_2),len(grid_param_1))
scores_sd = np.array(scores_sd).reshape(len(grid_param_2),len(grid_param_1))
# Set plot style
plt.style.use('seaborn')
# Plot Grid search scores
_, ax = plt.subplots(1,1)
if grid_param_2 is not None:
# Param1 is the X-axis, Param 2 is represented as a different curve (color line)
for idx, val in enumerate(grid_param_2):
ax.plot(grid_param_1, scores_mean[idx,:], '-o', label= name_param_2 + ': ' + str(val))
else:
# If only one Param1 is given
ax.plot(grid_param_1, scores_mean, '-o')
ax.set_title("Grid Search", fontsize=20, fontweight='normal')
ax.set_xlabel(name_param_1, fontsize=16)
ax.set_ylabel('CV Average ' + str.capitalize(metric), fontsize=16)
ax.legend(loc="best", fontsize=15)
ax.grid('on')
如您所见，我添加了支持包含多个指标的网格搜索的功能。您只需在调用绘图函数时指定要绘制的指标。
此外，如果您的网格搜索只调整了一个参数，您可以简单地为 grid_param_2 和 name_param_2.
指定 None调用如下：
plot_grid_search(grid_search.cv_results_,
'Accuracy',
list(np.linspace(0.001, 10, 50)),
['linear', 'rbf'],
'C',
'kernel')