UID 2 精华 积分 7736 威望 点
宅币 个
贡献 次
宅之契约 份
最后登录 1970-1-1
在线时间 小时
泰坦尼克生存数据集分类及调优https://www.kaggle.com/c/titanic/download/train.csv ) 共有891位乘客的数据信息，通过分析以下数据特征寻找与成功生存的关系：import pandas as pd # header=0指定第一行为表头 dataset = pd.read_csv('train.csv', header = 0) print("\n----------------- head -------------------") print(dataset.head()) print("\n----------------- info -------------------") print(dataset.info()) print("\n----------------- Sex -------------------") print(dataset["Sex"].value_counts()) print("\n----------------- Pclass -------------------") print(dataset["Pclass"].value_counts()) print("\n----------------- SibSp -------------------") print(dataset["SibSp"].value_counts()) print("\n----------------- Parch -------------------") print(dataset["Parch"].value_counts()) print("\n----------------- Embarked -------------------") print(dataset["Embarked"].value_counts()) 复制代码 import warnings warnings.filterwarnings("ignore") import time import numpy as np from sklearn.pipeline import Pipeline from sklearn.linear_model import * from sklearn.tree import * from sklearn.neighbors import * from sklearn.ensemble import * from sklearn.svm import * from sklearn.naive_bayes import * from sklearn.preprocessing import * from sklearn.cross_validation import train_test_split from sklearn.metrics import accuracy_score from sklearn.neural_network import * from sklearn.model_selection import * from sklearn.preprocessing import Imputer clfs = [ [LogisticRegression(max_iter=1000), {}], [SVC(), {'C': [0.1, 0.2, 0.5, 1.0, 2.0, 5.0, 10.0]}], [PassiveAggressiveClassifier(), {}], [RidgeClassifier(), {}], [RidgeClassifierCV(), {}], [SGDClassifier(), {}], [KNeighborsClassifier(n_neighbors=20), {}], [NearestCentroid(), {}], [DecisionTreeClassifier(), {}], [ExtraTreeClassifier(), {}], [AdaBoostClassifier(), {}], [BaggingClassifier(), {}], [ExtraTreeClassifier(), {}], [GradientBoostingClassifier(), {}], [RandomForestClassifier(n_estimators=100), {}], [BernoulliNB(), {}], [GaussianNB(), {}], ] pipes = [Pipeline([ ['sc', StandardScaler()], ['clf', GridSearchCV(pair[0], param_grid=pair[1])] ]) for pair in clfs] # 用于统一化初值处理、分类 def test_classifier(): for i in range(0, len(clfs)): minscore = 1.0 # 记录最小准确度用于后续进一步优化 start = time.time() acc_arr = [] for j in range(0, testnum): X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1) pipes[i].fit(X_train, y_train) y_pred = pipes[i].predict(X_test) acc_arr.append(accuracy_score(y_test, y_pred)) npacc = np.array(acc_arr) end = time.time() print('Accuraty:%s meanscore=%.2f minscore=%.2f time=%d' % (type(clfs[i][0]), npacc.mean(), npacc.min(), end - start)) dataset = pd.read_csv('train.csv', header = 0) # 由于Embarked只有2个缺失，用出现最多的S代替 dataset["Embarked"].fillna("S", inplace=True) # 编码Embarked字段 dataset["Embarked"] = LabelEncoder().fit_transform(dataset["Embarked"].values) # 编码Sex字段 dataset["Sex"]= LabelEncoder().fit_transform(dataset["Sex"].values) # Age缺失较多，这次用平均值代替 dataset["Age"].fillna(dataset["Age"].mean(), inplace=True) X = dataset[["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]].values y = dataset["Survived"].values testnum=100 test_classifier() 复制代码 from sklearn.ensemble import RandomForestRegressor dataset = pd.read_csv('train.csv', header = 0) dataset.drop("PassengerId", inplace=True, axis=1) dataset.drop("Name", inplace=True, axis=1) dataset.drop("Ticket", inplace=True, axis=1) dataset.drop("Cabin", inplace=True, axis=1) # 由于Embarked只有2个缺失，用出现最多的S代替 dataset["Embarked"].fillna("S", inplace=True) # 编码Embarked字段 dataset["Embarked"] = LabelEncoder().fit_transform(dataset["Embarked"].values) # 编码Sex字段 dataset["Sex"]= LabelEncoder().fit_transform(dataset["Sex"].values) # 使用随机森林预测缺失值，Age作为目标值进行预测 datasetxx = dataset[["Age", "Survived", "Pclass", "Sex", "SibSp", "Parch", "Fare", "Embarked"]] known_age = datasetxx[datasetxx["Age"].notnull()].as_matrix() unknown_age = datasetxx[datasetxx["Age"].isnull()].as_matrix() yy = known_age[:, 0] XX = known_age[:, 1:] rfr = RandomForestRegressor(random_state=0, n_estimators=2000, n_jobs=-1) rfr.fit(XX, yy) dataset["Age"][dataset["Age"].isnull()] = rfr.predict(unknown_age[:, 1:]) # 预测值写入数据集 X = dataset[["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]].values y = dataset["Survived"].values testnum=100 test_classifier() 复制代码 import re def get_ticket(ticket): out = re.compile("[0-9]+$").search(ticket) if out is None: return 0 else: return int(out.group(0)) dataset = pd.read_csv('train.csv', header = 0) # 由于Embarked只有2个缺失，用出现最多的S代替 dataset["Embarked"].fillna("S", inplace=True) # 编码Embarked字段 dataset["Embarked"] = LabelEncoder().fit_transform(dataset["Embarked"].values) # 编码Sex字段 dataset["Sex"]= LabelEncoder().fit_transform(dataset["Sex"].values) # Age缺失较多，这次用平均值代替 dataset["Age"].fillna(dataset["Age"].mean(), inplace=True) dataset['Ticket'] = dataset['Ticket'].apply(get_ticket) X = dataset[["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked", "Ticket"]].values y = dataset["Survived"].values testnum=100 test_classifier() 复制代码
|Archiver|小黑屋|技术宅的结界
( 滇ICP备16008837号 )|网站地图
发表于 2017-10-21 17:39:26
