#load data, review the fild and data type
import pandas as pddf_train = pd.read_csv('kaggle_bike_competition_train.csv',header=0)
df_train.head(5)
df_train.dtypes

datetime       object
season          int64
holiday         int64
workingday      int64
weather         int64
temp          float64
atemp         float64
humidity        int64
windspeed     float64
casual          int64
registered      int64
count           int64
dtype: object

#look the data rows,columns
df_train.shape

(10886, 12)

#看看有没有缺省的字段, 没有发现缺省值
df_train.count()

datetime      10886
season        10886
holiday       10886
workingday    10886
weather       10886
temp          10886
atemp         10886
humidity      10886
windspeed     10886
casual        10886
registered    10886
count         10886
dtype: int64

#来处理时间,因为它包含的信息总是非常多的,毕竟变化都是随着时间发生的嘛
df_train.head()
df_train['hour']=pd.DatetimeIndex(df_train.datetime).hour
df_train['day']=pd.DatetimeIndex(df_train.datetime).dayofweek
df_train['month']=pd.DatetimeIndex(df_train.datetime).month#other method
# df_train['dt']=pd.to_datetime(df_train['datetime'])
# df_train['day_of_week']=df_train['dt'].apply(lambda x:x.dayofweek)
# df_train['day_of_month']=df_train['dt'].apply(lambda x:x.day)df_train.head()

#提取 相关特征字段
# df = df_train.drop(['datetime','casual','registered'],axis=1,inplace=True)
df_train = df_train[['season','holiday','workingday','weather','temp','atemp','humidity','windspeed','count','month','day','hour']]
#df=df_train['datetime']
df_train.head(5)

df_train.shape

(10886, 12)

df_train_target = df_train['count'].values
print(df_train_target.shape)
df_train_data = df_train.drop(['count'],axis =1).values
print(df_train_data.shape)

from sklearn import linear_model
from sklearn import cross_validation
from sklearn import svm
from sklearn.ensemble import RandomForestRegressor
from sklearn.learning_curve import learning_curve
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import explained_variance_score# 切分一下数据（训练集和测试集）
cv = cross_validation.ShuffleSplit(len(df_train_data), n_iter=3, test_size=0.2,random_state=0)# 各种模型来一圈print("岭回归")
for train, test in cv:    svc = linear_model.Ridge().fit(df_train_data[train], df_train_target[train])print("train score: {0:.3f}, test score: {1:.3f}\n".format(svc.score(df_train_data[train], df_train_target[train]), svc.score(df_train_data[test], df_train_target[test])))print("支持向量回归/SVR(kernel='rbf',C=10,gamma=.001)")
for train, test in cv:svc = svm.SVR(kernel ='rbf', C = 10, gamma = .001).fit(df_train_data[train], df_train_target[train])print("train score: {0:.3f}, test score: {1:.3f}\n".format(svc.score(df_train_data[train], df_train_target[train]), svc.score(df_train_data[test], df_train_target[test])))print("随机森林回归/Random Forest(n_estimators = 100)")
for train, test in cv:    svc = RandomForestRegressor(n_estimators = 100).fit(df_train_data[train], df_train_target[train])print("train score: {0:.3f}, test score: {1:.3f}\n".format(svc.score(df_train_data[train], df_train_target[train]), svc.score(df_train_data[test], df_train_target[test])))

X = df_train_data
y = df_train_targetX_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.2, random_state=0)tuned_parameters = [{'n_estimators':[10,100,500,550]}]   scores = ['r2']for score in scores:print(score)clf = GridSearchCV(RandomForestRegressor(), tuned_parameters, cv=5, scoring=score)clf.fit(X_train, y_train)print("最佳参数找到了：")print("")#best_estimator_ returns the best estimator chosen by the searchprint(clf.best_estimator_)print("")print("得分分别是:")print("")#grid_scores_的返回值:#    * a dict of parameter settings#    * the mean score over the cross-validation folds #    * the list of scores for each foldfor params, mean_score, scores in clf.grid_scores_:print("%0.3f (+/-%0.03f) for %r"% (mean_score, scores.std() / 2, params))print("")