有谁知道如何在训练每个模型之前和之后放置秒表以评估哪个模型更快？
Does anyone know how to put a stopwatch before and after training each model to evaluate which one is faster?
我创建了贷款风险预测 python 机器学习模型来预测借款人是否能够支付银行贷款。我的模型运行良好，准确率为 78%。然而我的教授告诉我“
在训练每个模型之前和之后放一个秒表来评估哪个模型更快，甚至更好，在速度和准确性之间取得最好的权衡（我们想要快速和准确的模型）。 “，但我不知道如何在模型中添加秒表。我在互联网上搜索过这个东西，我没有得到任何关于如何在模型中放置秒表的信息。如果有人知道如何在模型中放置秒表，请告诉我在训练每个模型后
##我的Python预测模型
# Importing the Libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
from sklearn.preprocessing import StandardScaler
import seaborn as sns
sns.set(style="white", color_codes=True)
# Importimg the dataset and displaying first 10 values
data = pd.read_csv("credit_train.csv")
data.head(10)
# Find null values
data.isnull().sum()
# Drop null records
data = data.dropna(axis=0)
#To get basic information and statistics
data.describe()
# Check number of unique values
data["Home Ownership"].unique()
data["Home Ownership"].value_counts()
# Data Representation
sns.FacetGrid(data,hue="Loan Status",size=4) \
.map(plt.scatter,"Current Loan Amount","Monthly Debt") \
.add_legend()
plt.show()
# Categorical attributes visualization
sns.countplot(x="Loan Status",data=data)
sns.countplot(x="Term",data=data)
sns.countplot(x="Years in current job",data=data)
sns.countplot(x="Home Ownership",data=data)
sns.countplot(x="Loan Status",hue="Home Ownership",data=data)
sns.countplot(x="Loan Status",hue="Term",data=data)
# Numerical attributes visualization
sns.distplot(data['Current Loan Amount'])
sns.distplot(data['Annual Income'])
sns.distplot(data['Credit Score'])
sns.distplot(data['Monthly Debt'])
sns.distplot(data['Current Credit Balance'])
#Normalization and log transformation
data['Current Loan Amount Log'] = np.log(data['Current Loan Amount']+1)
sns.distplot(data["Current Loan Amount Log"])
data['Credit Score Log'] = np.log(data['Credit Score']+1)
sns.distplot(data["Credit Score Log"])
data['Annual Income Log'] = np.log(data['Annual Income']+1)
sns.distplot(data["Annual Income Log"])
data['Monthly Debt Log'] = np.log(data['Monthly Debt']+1)
sns.distplot(data["Monthly Debt Log"])
data['Current Credit Balance Log'] = np.log(data['Current Credit Balance']+1)
sns.distplot(data["Current Credit Balance Log"])
# Drop unnecessary columns
data = data.drop(['Loan ID', 'Customer ID', "Current Loan Amount", "Credit Score", "Annual Income", 'Years in current job', 'Current Credit Balance', 'Purpose', 'Monthly Debt'], axis=1)
# Correlation Matrix of the columns given below
cols = ['Credit Score Log','Annual Income Log','Monthly Debt Log',
'Current Credit Balance Log','Current Credit Balance Log','Current Loan Amount Log','Tax Liens','Years of Credit History', 'Maximum Open Credit']
f, ax = plt.subplots(figsize=(15, 10))
cm = np.corrcoef(df.values.T)
sns.set(font_scale=1.5)
hm = sns.heatmap(cm, cbar=True, annot=True, square=True, fmt='.2f', annot_kws={'size': 15}, yticklabels=cols, xticklabels=cols)
plt.show()
# Label Encoding
from sklearn.preprocessing import LabelEncoder
cols = ['Loan Status',"Term","Home Ownership"]
le = LabelEncoder()
for col in cols:
data[col] = le.fit_transform(data[col])
# data slicing
x = data.drop(columns=['Loan Status'], axis=1)
y = data['Loan Status']
# Train-Test Split
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=0)
# Random forest model
# Importing libraries and classes
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier()
model.fit(x_train,y_train)
# Find accuracy in training and testing model
model.score(x_train,y_train)
model.score(x_test,y_test)
# Predict the value of test dataset
predicted = model.predict(x_test)
# Generating Report
from sklearn import metrics
print(metrics.classification_report(y_test, predicted))
# Confusion Matrix
print(metrics.confusion_matrix(y_test, predicted))
from time import time
t_bef = time()
function()
t_aft = time()
print("function took", t_aft-t_bef, "seconds") # stmt1
print("function took", (t_aft-t_bef)*1000, "microseconds") # stmt2
您可以通过使用 time.time() 函数读取上下文中代码前后的时间来复制计时器。请注意，可能需要像 stmt2 中那样更改时间计算以获得精度。
我创建了贷款风险预测 python 机器学习模型来预测借款人是否能够支付银行贷款。我的模型运行良好，准确率为 78%。然而我的教授告诉我“ 在训练每个模型之前和之后放一个秒表来评估哪个模型更快，甚至更好，在速度和准确性之间取得最好的权衡（我们想要快速和准确的模型）。 “，但我不知道如何在模型中添加秒表。我在互联网上搜索过这个东西，我没有得到任何关于如何在模型中放置秒表的信息。如果有人知道如何在模型中放置秒表，请告诉我在训练每个模型后
##我的Python预测模型
# Importing the Libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
from sklearn.preprocessing import StandardScaler
import seaborn as sns
sns.set(style="white", color_codes=True)
# Importimg the dataset and displaying first 10 values
data = pd.read_csv("credit_train.csv")
data.head(10)
# Find null values
data.isnull().sum()
# Drop null records
data = data.dropna(axis=0)
#To get basic information and statistics
data.describe()
# Check number of unique values
data["Home Ownership"].unique()
data["Home Ownership"].value_counts()
# Data Representation
sns.FacetGrid(data,hue="Loan Status",size=4) \
.map(plt.scatter,"Current Loan Amount","Monthly Debt") \
.add_legend()
plt.show()
# Categorical attributes visualization
sns.countplot(x="Loan Status",data=data)
sns.countplot(x="Term",data=data)
sns.countplot(x="Years in current job",data=data)
sns.countplot(x="Home Ownership",data=data)
sns.countplot(x="Loan Status",hue="Home Ownership",data=data)
sns.countplot(x="Loan Status",hue="Term",data=data)
# Numerical attributes visualization
sns.distplot(data['Current Loan Amount'])
sns.distplot(data['Annual Income'])
sns.distplot(data['Credit Score'])
sns.distplot(data['Monthly Debt'])
sns.distplot(data['Current Credit Balance'])
#Normalization and log transformation
data['Current Loan Amount Log'] = np.log(data['Current Loan Amount']+1)
sns.distplot(data["Current Loan Amount Log"])
data['Credit Score Log'] = np.log(data['Credit Score']+1)
sns.distplot(data["Credit Score Log"])
data['Annual Income Log'] = np.log(data['Annual Income']+1)
sns.distplot(data["Annual Income Log"])
data['Monthly Debt Log'] = np.log(data['Monthly Debt']+1)
sns.distplot(data["Monthly Debt Log"])
data['Current Credit Balance Log'] = np.log(data['Current Credit Balance']+1)
sns.distplot(data["Current Credit Balance Log"])
# Drop unnecessary columns
data = data.drop(['Loan ID', 'Customer ID', "Current Loan Amount", "Credit Score", "Annual Income", 'Years in current job', 'Current Credit Balance', 'Purpose', 'Monthly Debt'], axis=1)
# Correlation Matrix of the columns given below
cols = ['Credit Score Log','Annual Income Log','Monthly Debt Log',
'Current Credit Balance Log','Current Credit Balance Log','Current Loan Amount Log','Tax Liens','Years of Credit History', 'Maximum Open Credit']
f, ax = plt.subplots(figsize=(15, 10))
cm = np.corrcoef(df.values.T)
sns.set(font_scale=1.5)
hm = sns.heatmap(cm, cbar=True, annot=True, square=True, fmt='.2f', annot_kws={'size': 15}, yticklabels=cols, xticklabels=cols)
plt.show()
# Label Encoding
from sklearn.preprocessing import LabelEncoder
cols = ['Loan Status',"Term","Home Ownership"]
le = LabelEncoder()
for col in cols:
data[col] = le.fit_transform(data[col])
# data slicing
x = data.drop(columns=['Loan Status'], axis=1)
y = data['Loan Status']
# Train-Test Split
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=0)
# Random forest model
# Importing libraries and classes
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier()
model.fit(x_train,y_train)
# Find accuracy in training and testing model
model.score(x_train,y_train)
model.score(x_test,y_test)
# Predict the value of test dataset
predicted = model.predict(x_test)
# Generating Report
from sklearn import metrics
print(metrics.classification_report(y_test, predicted))
# Confusion Matrix
print(metrics.confusion_matrix(y_test, predicted))
from time import time
t_bef = time()
function()
t_aft = time()
print("function took", t_aft-t_bef, "seconds") # stmt1
print("function took", (t_aft-t_bef)*1000, "microseconds") # stmt2
您可以通过使用 time.time() 函数读取上下文中代码前后的时间来复制计时器。请注意，可能需要像 stmt2 中那样更改时间计算以获得精度。