阿里云天池大赛赛题解析

一个程序袁
于 2024-06-07 18:46:38 发布
阅读量372
点赞数 1
文章标签：机器学习人工智能深度学习 python
本文链接：https://blog.csdn.net/m0_69184465/article/details/139533818
版权
#%% md

## 导入数据分析工具包

#%%

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

from scipy import stats

import warnings
warnings.filterwarnings("ignore")
 
%matplotlib inline

#%% md

## 数据读取

#%%

train_data_file = "./zhengqi_train.txt"
test_data_file =  "./zhengqi_test.txt"

train_data = pd.read_csv(train_data_file, sep='\t', encoding='utf-8')
test_data = pd.read_csv(test_data_file, sep='\t', encoding='utf-8')

#%% md

## 训练数据总览

#%%

train_data.describe()

#%% md

## 异常值分析

#%%

plt.figure(figsize=(18, 10))
plt.boxplot(x=train_data.values,labels=train_data.columns)
plt.hlines([-7.5, 7.5], 0, 40, colors='r')
plt.show()

#%% md

## 删除异常值

#%%

train_data = train_data[train_data['V9']>-7.5]
train_data.describe()

#%%

test_data.describe()

#%% md

## 最大最小值归一化

#%%

from sklearn import preprocessing 

features_columns = [col for col in train_data.columns if col not in ['target']]

min_max_scaler = preprocessing.MinMaxScaler()

min_max_scaler = min_max_scaler.fit(train_data[features_columns])

train_data_scaler = min_max_scaler.transform(train_data[features_columns])
test_data_scaler = min_max_scaler.transform(test_data[features_columns])

train_data_scaler = pd.DataFrame(train_data_scaler)
train_data_scaler.columns = features_columns

test_data_scaler = pd.DataFrame(test_data_scaler)
test_data_scaler.columns = features_columns

train_data_scaler['target'] = train_data['target']

#%%

train_data_scaler.describe()

#%%

test_data_scaler.describe()

#%% md

## 查看训练集数据和测试集数据分布情况

#%%

dist_cols = 6
dist_rows = len(test_data_scaler.columns)

plt.figure(figsize=(4*dist_cols,4*dist_rows))


for i, col in enumerate(test_data_scaler.columns):
    ax=plt.subplot(dist_rows,dist_cols,i+1)
    ax = sns.kdeplot(train_data_scaler[col], color="Red", shade=True)
    ax = sns.kdeplot(test_data_scaler[col], color="Blue", shade=True)
    ax.set_xlabel(col)
    ax.set_ylabel("Frequency")
    ax = ax.legend(["train","test"])
 
plt.show()

#%% md

查看特征'V5', 'V17', 'V28', 'V22', 'V11', 'V9'数据的数据分布

#%%

drop_col = 6
drop_row = 1

plt.figure(figsize=(5*drop_col,5*drop_row))

for i, col in enumerate(["V5","V9","V11","V17","V22","V28"]):
    ax =plt.subplot(drop_row,drop_col,i+1)
    ax = sns.kdeplot(train_data_scaler[col], color="Red", shade=True)
    ax= sns.kdeplot(test_data_scaler[col], color="Blue", shade=True)
    ax.set_xlabel(col)
    ax.set_ylabel("Frequency")
    ax = ax.legend(["train","test"])
plt.show()

#%% md

这几个特征下，训练集的数据和测试集的数据分布不一致，会影响模型的泛化能力，故删除这些特征

#%% md

## 特征相关性

#%%

plt.figure(figsize=(20, 16))  
column = train_data_scaler.columns.tolist()  
mcorr = train_data_scaler[column].corr(method="spearman")  
mask = np.zeros_like(mcorr, dtype=np.bool_)  
mask[np.triu_indices_from(mask)] = True  
cmap = sns.diverging_palette(220, 10, as_cmap=True)  
g = sns.heatmap(mcorr, mask=mask, cmap=cmap, square=True, annot=True, fmt='0.2f')  
plt.show()

#%% md

# 特征降维

#%% md

## 相关新分析

#%%

mcorr=mcorr.abs()
numerical_corr=mcorr[mcorr['target']>0.1]['target']
print(numerical_corr.sort_values(ascending=False))

index0 = numerical_corr.sort_values(ascending=False).index
print(train_data_scaler[index0].corr('spearman'))

#%% md

## 相关性初筛

#%%

features_corr = numerical_corr.sort_values(ascending=False).reset_index()
features_corr.columns = ['features_and_target', 'corr']
features_corr_select = features_corr[features_corr['corr']>0.3] # 筛选出大于相关性大于0.3的特征
print(features_corr_select)
select_features = [col for col in features_corr_select['features_and_target'] if col not in ['target']]
new_train_data_corr_select = train_data_scaler[select_features+['target']]
new_test_data_corr_select = test_data_scaler[select_features]

#%% md

## 多重共线性分析

#%%

from statsmodels.stats.outliers_influence import variance_inflation_factor #多重共线性方差膨胀因子

#多重共线性
new_numerical=['V0', 'V2', 'V3', 'V4', 'V5', 'V6', 'V10','V11', 
                         'V13', 'V15', 'V16', 'V18', 'V19', 'V20', 'V22','V24','V30', 'V31', 'V37']
X=np.matrix(train_data_scaler[new_numerical])
VIF_list=[variance_inflation_factor(X, i) for i in range(X.shape[1])]
VIF_list

#%% md

## PCA去除多重共线性 降维

#%%

from sklearn.decomposition import PCA   #主成分分析法

#PCA方法降维
#保持90%的信息
pca = PCA(n_components=0.9)
new_train_pca_90 = pca.fit_transform(train_data_scaler.iloc[:,0:-1])
new_test_pca_90 = pca.transform(test_data_scaler)
new_train_pca_90 = pd.DataFrame(new_train_pca_90)
new_test_pca_90 = pd.DataFrame(new_test_pca_90)
new_train_pca_90['target'] = train_data_scaler['target']
new_train_pca_90.describe()

#%%

#PCA方法降维
#保留16个主成分
pca = PCA(n_components=16)
new_train_pca_16 = pca.fit_transform(train_data_scaler.iloc[:,0:-1])
new_test_pca_16 = pca.transform(test_data_scaler)
new_train_pca_16 = pd.DataFrame(new_train_pca_16)
new_test_pca_16 = pd.DataFrame(new_test_pca_16)
new_train_pca_16['target'] = train_data_scaler['target']
new_train_pca_16.describe()

#%% md

## 模型训练

#%% md

### 导入相关库

#%%

from sklearn.linear_model import LinearRegression  #线性回归
from sklearn.neighbors import KNeighborsRegressor  #K近邻回归
from sklearn.tree import DecisionTreeRegressor     #决策树回归
from sklearn.ensemble import RandomForestRegressor #随机森林回归
from sklearn.svm import SVR  #支持向量回归
import lightgbm as lgb #lightGbm模型

from sklearn.model_selection import train_test_split # 切分数据
from sklearn.metrics import mean_squared_error #评价指标

from sklearn.model_selection import learning_curve
from sklearn.model_selection import ShuffleSplit


#%% md

### 切分训练数据和线下验证数据

#%%

#采用 pca 保留16维特征的数据
new_train_pca_16 = new_train_pca_16.fillna(0)
train = new_train_pca_16[new_test_pca_16.columns]
target = new_train_pca_16['target']

# 切分数据 训练数据80% 验证数据20%
train_data,test_data,train_target,test_target=train_test_split(train,target,test_size=0.2,random_state=0)

#%% md

### 定义绘制模型学习曲线函数

#%%

def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
                        n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
    plt.figure()
    plt.title(title)
    if ylim is not None:
        plt.ylim(*ylim)
    plt.xlabel("Training examples")
    plt.ylabel("Score")
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
    train_scores_mean = np.mean(train_scores, axis=1)
    train_scores_std = np.std(train_scores, axis=1)
    test_scores_mean = np.mean(test_scores, axis=1)
    test_scores_std = np.std(test_scores, axis=1)
    
    print(train_scores_mean)
    print(test_scores_mean)
    
    plt.grid()
 
    plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
                     train_scores_mean + train_scores_std, alpha=0.1,
                     color="r")
    plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
                     test_scores_mean + test_scores_std, alpha=0.1, color="g")
    plt.plot(train_sizes, train_scores_mean, 'o-', color="r",
             label="Training score")
    plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
             label="Cross-validation score")
 
    plt.legend(loc="best")
    return plt

#%% md

### 多元线性回归模型

#%%

clf = LinearRegression()
clf.fit(train_data, train_target)
score = mean_squared_error(test_target, clf.predict(test_data))
print("LinearRegression:   ", score)

#%% md

### 绘制线性回归模型学习曲线

#%%


X = train_data.values
y = train_target.values
 
# 图一
title = r"LinearRegression"
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)
estimator = LinearRegression()    #建模
plot_learning_curve(estimator, title, X, y, ylim=(0.5, 0.8), cv=cv, n_jobs=1)


#%% md

### K近邻回归

#%%

clf = KNeighborsRegressor(n_neighbors=8) # 最近三个
clf.fit(train_data, train_target)
score = mean_squared_error(test_target, clf.predict(test_data))
print("KNeighborsRegressor:   ", score)

#%% md

### 绘制K近邻回归学习曲线

#%%

X = train_data.values
y = train_target.values
 
# K近邻回归
title = r"KNeighborsRegressor"
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)

estimator = KNeighborsRegressor(n_neighbors=8)    #建模
plot_learning_curve(estimator, title, X, y, ylim=(0.3, 0.9), cv=cv, n_jobs=1)

#%% md

### 决策树回归

#%%

clf = DecisionTreeRegressor() 
clf.fit(train_data, train_target)

score = mean_squared_error(test_target, clf.predict(test_data))
print("DecisionTreeRegressor:   ", score)

#%% md

### 绘制决策树学习曲线

#%%

X = train_data.values
y = train_target.values
 
# 决策树回归
title = r"DecisionTreeRegressor"
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)

estimator = DecisionTreeRegressor()    #建模
plot_learning_curve(estimator, title, X, y, ylim=(0.1, 1.3), cv=cv, n_jobs=1)

#%% md

### 随机森林回归

#%%

clf = RandomForestRegressor(n_estimators=200) # 200棵树模型
clf.fit(train_data, train_target)
score = mean_squared_error(test_target, clf.predict(test_data))
print("RandomForestRegressor:   ", score)

#%% md

### 绘制随机森林回归学习曲线

#%%

X = train_data.values
y = train_target.values
 
# K近邻回归
title = r"RandomForestRegressor"
cv = ShuffleSplit(n_splits=5, test_size=0.2, random_state=0)

estimator = RandomForestRegressor(n_estimators=200)    #建模
plot_learning_curve(estimator, title, X, y, ylim=(0.4, 1.0), cv=cv, n_jobs=1)

#%% md

### lgb模型回归

#%%

# lgb回归模型
clf = lgb.LGBMRegressor(
        learning_rate=0.01,
        max_depth=-1,
        n_estimators=5000,
        boosting_type='gbdt',
        random_state=2019,
        objective='regression',
    )

# 训练模型
clf.fit(
        X=train_data, y=train_target,
        eval_metric='MSE'
       
    )

score = mean_squared_error(test_target, clf.predict(test_data))
print("lightGbm:   ", score)

#%%
需要数据集的请评论区留言哦