def main():
feature.main()
'''
利用网格搜索选择参数，时间较长，可以不运行
'''
# params.main()
'''
利用最后一星期的数据来测试模型的效果
'''
test.main()
'''
预测结果
'''
predict.main()
def which_mode():
while (1):
wh=ad.stt()
if wh is None:
ad.tts( "try again")
continue
if ad.find(wh,"read"):
ad.tts("ok, I am ready to assist you in reading.")
a= feature.main(1)
return a;
elif ( ad.find(wh,"sketch") or ad.find(wh,"draw") ):
ad.tts("ok, I am ready to assist you in sketching.")
#sketch()
return;
elif ( ad.find(wh,"note") or ad.find(wh,"write") ):
ad.tts("ok, I am ready to assist you in taking notes.")
#note()
return;
else:
ad.tts("Sorry, I didn't get you. Are you reading or sketching or taking notes?")
which_mode()
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import VotingClassifier
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.preprocessing import normalize
import feature as ft
with open('pickles/train_df.pickle', 'rb') as f:
train_df = pickle.load(f)
test_df = pd.read_csv('test.csv')
X = ft.main(train_df)
y = train_df['Survived']
normalize(X, copy=False)
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.2, random_state=4)
svm = SVC(probability=True, C=3)
svm.fit(X_train, y_train)
knn = KNeighborsClassifier(metric='minkowski', n_neighbors=70, p=1, weights='distance')
knn.fit(X_train, y_train)
grad = GradientBoostingClassifier(learning_rate=0.1, max_depth=2, max_features=2, n_estimators=400, subsample=1.0)
grad.fit(X_train, y_train)
# -*- coding: utf-8 -*-
import pandas as pd, numpy as np, plotting, pickle
from sklearn import cross_validation
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score
from sklearn import preprocessing
import feature as ft
with open('pickles/eclf.pickle', 'rb') as f:
clf = pickle.load(f)
with open('pickles/test_df.pickle', 'rb') as f:
test_df = pickle.load(f)
test_df.drop([759], inplace=True)
test_df.set_value(414, 'Title', 'Aristocratic')
X = ft.main(test_df.copy())
pred = clf.predict(X)
Titanic_predictions = pd.DataFrame(test_df['PassengerId'], dtype=int)
Titanic_predictions['Survived'] = pred
print Titanic_predictions.head()
Titanic_predictions.to_csv('Titanic_predictions.csv', index_label=False, index=False)
prd = pd.read_csv('Titanic_predictions.csv')
print prd.head()
print "Columns", X.columns.values
