from sklearn.datasets import load_iris, fetch_20newsgroups, load_boston
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.neighbors import KNeighborsClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier, export_graphviz
from sklearn.ensemble import RandomForestClassifier
import pandas as pd
def knncls():
"""
K-近邻预测用户签到位置
:return:None
"""
data = pd.read_csv("./data/FBlocation/train.csv")
data = data.query("x > 1.0 & x < 1.25 & y > 2.5 & y < 2.75")
time_value = pd.to_datetime(data['time'], unit='s')
print(time_value)
time_value = pd.DatetimeIndex(time_value)
data['day'] = time_value.day
data['hour'] = time_value.hour
data['weekday'] = time_value.weekday
data = data.drop(['time'], axis=1)
print(data)
place_count = data.groupby('place_id').count()
tf = place_count[place_count.row_id > 3].reset_index()
data = data[data['place_id'].isin(tf.place_id)]
y = data['place_id']
x = data.drop(['place_id'], axis=1)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)
std = StandardScaler()
x_train = std.fit_transform(x_train)
x_test = std.transform(x_test)
knn = KNeighborsClassifier()
param = {"n_neighbors": [3, 5, 10]}
gc = GridSearchCV(knn, param_grid=param, cv=2)
gc.fit(x_train, y_train)
print("在测试集上准确率：", gc.score(x_test, y_test))
print("在交叉验证当中最好的结果：", gc.best_score_)
print("选择最好的模型是：", gc.best_estimator_)
print("每个超参数每次交叉验证的结果：", gc.cv_results_)
return None
def naviebayes():
"""
朴素贝叶斯进行文本分类
:return: None
"""
news = fetch_20newsgroups(subset='all')
x_train, x_test, y_train, y_test = train_test_split(news.data, news.target, test_size=0.25)
tf = TfidfVectorizer()
x_train = tf.fit_transform(x_train)
print(tf.get_feature_names())
x_test = tf.transform(x_test)
mlt = MultinomialNB(alpha=1.0)
print(x_train.toarray())
mlt.fit(x_train, y_train)
y_predict = mlt.predict(x_test)
print("预测的文章类别为：", y_predict)
print("准确率为：", mlt.score(x_test, y_test))
print("每个类别的精确率和召回率：", classification_report(y_test, y_predict, target_names=news.target_names))
return None
def decision():
"""
决策树对泰坦尼克号进行预测生死
:return: None
"""
titan = pd.read_csv("http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt")
x = titan[['pclass', 'age', 'sex']]
y = titan['survived']
print(x)
x['age'].fillna(x['age'].mean(), inplace=True)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)
dict = DictVectorizer(sparse=False)
x_train = dict.fit_transform(x_train.to_dict(orient="records"))
print(dict.get_feature_names())
x_test = dict.transform(x_test.to_dict(orient="records"))
rf = RandomForestClassifier(n_jobs=-1)
param = {"n_estimators": [120, 200, 300, 500, 800, 1200], "max_depth": [5, 8, 15, 25, 30]}
gc = GridSearchCV(rf, param_grid=param, cv=2)
gc.fit(x_train, y_train)
print("准确率：", gc.score(x_test, y_test))
print("查看选择的参数模型：", gc.best_params_)
return None
if __name__ == "__main__":
decision()
