【人工智能项目】深度学习实现白葡萄酒品质预测

任务介绍

评价一款葡萄酒时不外乎从颜色、酸度、甜度、香气、风味等入手，而决定这些就是葡萄酒的挥发酸度、糖分、密度等。

根据给出的白葡萄酒酸度、糖分、PH值、柠檬酸等数据，判断葡萄酒品质。

导入数据

import numpy as np
import pandas as pd
import warnings
warnings.filterwarnings("ignore")

train_data = pd.read_csv("./winequality_dataset/train.csv",header=0,index_col=None)

train_data.head()

EDA

train_data.info()

train_data.isnull().sum()

import matplotlib.pyplot as plt
%matplotlib inlinefig = plt.figure()
ax = fig.add_subplot(111)
ax.set(xlabel="total sulfur dioxide",ylabel="free sulfur dioxide")
ax.scatter(train_data["total sulfur dioxide"],train_data["free sulfur dioxide"],c="r")
plt.show()

数据集划分

from sklearn.model_selection import train_test_splitX = train_data.iloc[:,:-1]
y = np.ravel(train_data.quality)X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=2019)

X.head()

print(X_train.shape)
print(y_train.shape)
print(X_test.shape)
print(y_test.shape)

(5517, 11)
(5517,)
(1380, 11)
(1380,)

数据预处理

from sklearn.preprocessing import PolynomialFeaturesprint("Shape of X_train before transformation:",X_train.shape)
poly = PolynomialFeatures(degree=2,include_bias=False)
X_train_poly = poly.fit_transform(X_train)
X_test_poly = poly.transform(X_test)
X_poly = poly.transform(X)
print("Shape of X_train after transformation:",X_train_poly.shape)

Shape of X_train before transformation: (3200, 11)
Shape of X_train after transformation: (3200, 77

from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import MinMaxScalerscaler = MinMaxScaler().fit(X_train_poly)
X_train = scaler.transform(X_train_poly)
X_test = scaler.transform(X_test_poly)X = scaler.transform(X_poly)

数据归一化处理

from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import MinMaxScalerscaler = MinMaxScaler().fit(X_train)
X_train = scaler.transform(X_train)
X_test = scaler.transform(X_test)X = scaler.transform(X)

ML模型

# 传统机器方法大杂烩
from sklearn.preprocessing import StandardScaler,RobustScaler
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_scorefrom sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC
from sklearn.discriminant_analysis import LinearDiscriminantAnalysisfrom catboost import CatBoostClassifierfrom sklearn.metrics import accuracy_score,confusion_matrix,classification_report

def get_models():models = []models.append(("LR",LogisticRegression()))models.append(("NB",GaussianNB()))models.append(("KNN",KNeighborsClassifier()))models.append(("DT",DecisionTreeClassifier()))models.append(("SVM rbf",SVC()))models.append(("SVM linear",SVC(kernel="linear")))models.append(("LDA",LinearDiscriminantAnalysis()))models.append(("Cat",CatBoostClassifier(silent=True)))return modelsdef cross_validation_scores_for_various_ml_models(X_cv,y_cv):print("cross validation accuracy".upper())models = get_models()results = []names = []for name,model in models:kfold = KFold(n_splits=5,shuffle=True,random_state=2019)cv_result = cross_val_score(model,X_cv,y_cv,cv=kfold,scoring="accuracy")names.append(name)results.append(cv_result)print("{}cross validation,accuracy:{:0.2f}".format(name,cv_result.mean()))

cross_validation_scores_for_various_ml_models(X,y)

Random Forest

from sklearn.model_selection import train_test_split,cross_val_score,GridSearchCV
from sklearn.metrics import mean_absolute_error,classification_report
from sklearn.ensemble import RandomForestClassifier,RandomForestRegressor
from xgboost import XGBRegressor

scores = {}for n_estimators in range(10,810,10):RF_model = RandomForestClassifier(n_estimators=n_estimators,random_state=2019)RF_model.fit(X_train,y_train)RF_predictions = RF_model.predict(X_test)RF_mae = mean_absolute_error(RF_predictions,y_test)scores[n_estimators] = RF_mae

import matplotlib.pyplot as plt
%matplotlib inlinefig_RF,ax_RF = plt.subplots(figsize=(10,4))
ax_RF.set_title("Mean Absolute Error with Number of Estimators of a Random Forest")
ax_RF.set_xlabel("Number of Estimators")
ax_RF.set_ylabel("Mean Absolute Error")
plt.plot(list(scores.keys()),list(scores.values()))

best_n_estimators = 0for n_estimators,score in scores.items():if score == min(scores.values()):best_n_estimators = n_estimatorsprint(f"Best Number of Estimators:{n_estimators}")

RF_model = RandomForestClassifier(n_estimators=best_n_estimators,random_state=2019)
RF_model.fit(X_train,y_train)
RF_predictions = RF_model.predict(X_test)
RF_mae = mean_absolute_error(RF_predictions,y_test)print(f"Mean Absolute Error:{RF_mae}")
print(classification_report(y_test,RF_predictions))

from sklearn.model_selection import GridSearchCVparam_grid = {"n_estimators":[120,140,300,500,800,1200]}
RF_model_new = RandomForestClassifier(random_state=2019)
RF_grid = GridSearchCV(RF_model_new,param_grid,verbose=1,n_jobs=-1,cv=3,scoring="neg_mean_absolute_error")
RF_grid.fit(X_train,y_train)

RF_grid.best_params_

RF_model = RandomForestClassifier(n_estimators=140,random_state=2019)
RF_model.fit(X_train,y_train)
RF_predictions = RF_model.predict(X_test)
RF_mae = mean_absolute_error(RF_predictions,y_test)print(f"Mean Absolute Error:{RF_mae}")
print(classification_report(y_test,RF_predictions))

ExtraTreeClassifier

from sklearn.ensemble import ExtraTreesClassifier
from sklearn.ensemble import ExtraTreesRegressor

scores = {}for n_estimators in range(10,600,10):extra_model = ExtraTreesClassifier(n_estimators=n_estimators,random_state=2019)extra_model.fit(X_train,y_train)extra_predictions = extra_model.predict(X_test)extra_mae = mean_absolute_error(extra_predictions,y_test)scores[n_estimators] = extra_mae

import matplotlib.pyplot as plt
%matplotlib inlinefig_RF,ax_RF = plt.subplots(figsize=(10,4))
ax_RF.set_title("Mean Absolute Error with Number of Estimators of a Random Forest")
ax_RF.set_xlabel("Number of Estimators")
ax_RF.set_ylabel("Mean Absolute Error")
plt.plot(list(scores.keys()),list(scores.values()))

best_n_estimators = 0for n_estimators,score in scores.items():if score == min(scores.values()):best_n_estimators = n_estimatorsprint(f"Best Number of Estimators:{n_estimators}")

Best Number of Estimators:150

extra_classifier = ExtraTreesClassifier(n_estimators=530,random_state=2019)
extra_classifier = extra_classifier.fit(X_train,y_train)
extra_classifier_prediction = extra_classifier.predict(X_test)
extra_mae = mean_absolute_error(extra_classifier_prediction,y_test)
print(f"Mean Absolute Error:{extra_mae}")

Mean Absolute Error:0.16304347826086957

Ensemble
K-Nearest Neighbors

from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import RandomizedSearchCV
import scipy.stats as st
from sklearn.neighbors import KNeighborsClassifierparam_grid = {"n_neighbors":st.randint(1,40),"weights":["uniform","distance"]}KN_model = KNeighborsClassifier()
KN_grid = RandomizedSearchCV(KN_model,param_grid,verbose=1,n_jobs=-1,cv=3)
KN_grid.fit(X_train,y_train)

print(KN_grid.best_params_)

{‘n_neighbors’: 32, ‘weights’: ‘distance’}

KN_model = KNeighborsClassifier(n_neighbors=30,weights="distance")
KN_model.fit(X_train,y_train)
KN_predictions = KN_model.predict(X_test)
KN_mae = mean_absolute_error(KN_predictions,y_test)print(f"Mean Absolute Error:{KN_mae}")

Mean Absolute Error:0.5441176470588235

Logistic Regression

from sklearn.linear_model import LogisticRegressionlogistic_regression = LogisticRegression()
logistic_regression.fit(X_train,y_train)
logistic_prediction = logistic_regression.predict(X_test)
logistic_mae = mean_absolute_error(logistic_prediction,y_test)
print(f"Mean Absolute Error:{logistic_mae}")

Mean Absolute Error:0.5970588235294118

LinearRegression

from sklearn.linear_model import LinearRegressionlin_regression = LinearRegression()
lin_regression.fit(X_train,y_train)
lin_prediction = lin_regression.predict(X_test)
lin_mae = mean_absolute_error(lin_prediction,y_test)
print(f"Mean Absolute Error:{lin_mae}")

Mean Absolute Error:0.6353137915187634

ElasticNet

from sklearn.linear_model import ElasticNetela_regression = ElasticNet()
ela_regression.fit(X_train,y_train)
els_prediction = ela_regression.predict(X_test)
ela_mae = mean_absolute_error(els_prediction,y_test)
print(f"Mean Absolute Error:{ela_mae}")

Mean Absolute Error:0.698948525093073

PolynomialFeatures

from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegressionpoly_features = PolynomialFeatures(degree=5,include_bias=False)X_train_poly = poly_features.fit_transform(X_train)
X_test_poly = poly_features.transform(X_test)

poly_reg = LinearRegression()
poly_reg.fit(X_train_poly,y_train)
poly_reg_prediction = poly_reg.predict(X_test_poly)
poly_reg_mae = mean_absolute_error(poly_reg_prediction,y_test)
print(f"Mean Absolute Error:{poly_reg_mae}")

Mean Absolute Error:19.971436771294478

DL模型

# 模型定义
from keras.models import Sequential
from keras.layers import Dense,Dropoutmodel = Sequential()# model.add(Dense(128,activation="relu"))
# model.add(Dropout(0.2))
# model.add(Dense(64,activation="relu"))
# model.add(Dropout(0.2))
model.add(Dense(32,activation="relu"))
model.add(Dropout(0.2))
model.add(Dense(16,activation="relu"))
model.add(Dropout(0.2))
model.add(Dense(1))

from keras.callbacks import EarlyStopping,ReduceLROnPlateau,ModelCheckpoint,LearningRateSchedulercheckpoint = ModelCheckpoint("dl.h5",monitor="val_loss",mode="min",save_best_only = True,verbose=1)earlystop = EarlyStopping(monitor = 'val_loss', min_delta = 0, patience = 5,verbose = 1,restore_best_weights = True)reduce_lr = ReduceLROnPlateau(monitor = 'val_loss',factor = 0.2,patience = 3,verbose = 1)#min_delta = 0.00001)callbacks = [earlystop, checkpoint, reduce_lr]

# 模型编译
model.compile(loss="mae",optimizer="adam",metrics=["mae"])

# 模型训练
model.fit(X_train,y_train,epochs=100,batch_size=1,verbose=1,validation_data=(X_test,y_test),callbacks=callbacks)

【人工智能项目】深度学习实现白葡萄酒品质预测相关推荐

热门 | Google Brain前员工深度盘点2017人工智能和深度学习各大动态
翻译 | AI科技大本营参与 | shawn 编辑 | Donna 2017年是人工智能井喷的一年.Google Brain团队前成员Denny Britz在自己的博客WILDML上对过去一年人工智 ...
H2O机器学习：一种强大的可扩展的人工智能和深度学习技术
书名:基于H2O的机器学习实用方法:一种强大的可扩展的人工智能和深度学习技术原书名:Practical Machine Learning with H2O:Powerful, Scalable Te ...
深度学习决策支持时空预测_重工业的预测性维护和决策支持系统
深度学习决策支持时空预测 Digital transformation is one of the top priorities for industrial companies. The larg ...
【人工智能】深度学习、数据库选择和人工智能的革命；人工智能是解锁IoT潜力的钥匙
深度学习(DL)和人工智能(AI)已经不再是科幻小说中遥不可及的目标,目前已成为了互联网和大数据等领域的前沿研究内容. 由于云计算提供强的计算能力.提出的先进算法以及充裕的资金,这创造了五年前难以想象 ...
人工智能和深度学习发展趋势_AI在学习和发展中的作用
人工智能和深度学习发展趋势 In this series of blogs, AI in HR, we already understood what is AI, what is HR and be ...
深度学习(一): 人工智能-机器学习-深度学习的区别
人工智能-机器学习-深度学习他们之间是有区别的先来一张图做一下解释从发展历史上来看 AI:让机器展现出人类智力回到1956年夏天,在当时的会议上,AI先驱的梦想是建造一台复杂的机器(让当时刚出 ...
2018 年，关于深度学习的 10 个预测
我有一种预感:2018年,所有的事情都会发生巨变.我们在2017年看到的深度学习取得的惊人突破将会以一种强大的方式延续到2018年.2017年在深度学习领域的研究成果将会应用于日常的软件应用中. 下面 ...
图解人工智能机器学习深度学习的关系和区别
图解人工智能机器学习深度学习的关系和区别,先直观看下图的关系: AI(Artificial Intelligence.人工智能).机器学习(machine learning).深度学习(Deep le ...
AlphaGo、人工智能、深度学习解读以及应用
经过几天的比拼,AlphaGo最终还是胜出,创造了人机大战历史上的一个新的里程碑.几乎所有的人都在谈论这件事情,这使得把"人工智能"."深度学习"的热潮推向了新 ...

【人工智能项目】深度学习实现白葡萄酒品质预测

【人工智能项目】深度学习实现白葡萄酒品质预测

任务介绍

导入数据

EDA

数据集划分

数据预处理

ML模型

DL模型

【人工智能项目】深度学习实现白葡萄酒品质预测相关推荐

最新文章

热门文章