House Priceの分析5

大まかな流れを把握

読み込み

#import some necessary librairies

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
%matplotlib inline
import matplotlib.pyplot as plt  # Matlab-style plotting
import seaborn as sns
color = sns.color_palette()
sns.set_style('darkgrid')
import warnings
def ignore_warn(*args, **kwargs):
    pass
warnings.warn = ignore_warn #ignore annoying warning (from sklearn and seaborn)


from scipy import stats
from scipy.stats import norm, skew #for some statistics


pd.set_option('display.float_format', lambda x: '{:.3f}'.format(x)) #Limiting floats output to 3 decimal points


from subprocess import check_output
print(check_output(["ls", "kaggle/kaggle1/"]).decode("utf8")) #check the files available in the directory

train = pd.read_csv('kaggle/kaggle1/train.csv')
test = pd.read_csv('kaggle/kaggle1/test.csv')

前処理

Idを消す

#check the numbers of samples and features
print("The train data size before dropping Id feature is : {} ".format(train.shape))
print("The test data size before dropping Id feature is : {} ".format(test.shape))

#Save the 'Id' column
train_ID = train['Id']
test_ID = test['Id']

#Now drop the  'Id' colum since it's unnecessary for  the prediction process.
train.drop("Id", axis = 1, inplace = True)
test.drop("Id", axis = 1, inplace = True)

#check again the data size after dropping the 'Id' variable
print("\nThe train data size after dropping Id feature is : {} ".format(train.shape)) 
print("The test data size after dropping Id feature is : {} ".format(test.shape))

SalePriceの外れ値削除

fig, ax = plt.subplots()
ax.scatter(x = train['GrLivArea'], y = train['SalePrice'])
plt.ylabel('SalePrice', fontsize=13)
plt.xlabel('GrLivArea', fontsize=13)
plt.show()

#Deleting outliers
train = train.drop(train[(train['GrLivArea']>4000) & (train['SalePrice']<300000)].index)

#Check the graphic again
fig, ax = plt.subplots()
ax.scatter(train['GrLivArea'], train['SalePrice'])
plt.ylabel('SalePrice', fontsize=13)
plt.xlabel('GrLivArea', fontsize=13)
plt.show()

SalePriceのhistgramと対数変換の確認

sns.distplot(train['SalePrice'] , fit=norm);

sns.distplot(train['SalePrice'] , fit=norm);
(mu, sigma) = norm.fit(train['SalePrice'])
print( '\n mu = {:.2f} and sigma = {:.2f}\n'.format(mu, sigma))

plt.legend(['Normal dist. ($\mu=$ {:.2f} and $\sigma=$ {:.2f} )'.format(mu, sigma)],
            loc='best')
plt.ylabel('Frequency')
plt.title('SalePrice distribution')

#Get also the QQ-plot
fig = plt.figure()
res = stats.probplot(train['SalePrice'], plot=plt)
plt.show()

#We use the numpy fuction log1p which  applies log(1+x) to all elements of the column
train["SalePrice"] = np.log1p(train["SalePrice"])

#Check the new distribution 
sns.distplot(train['SalePrice'] , fit=norm);

# Get the fitted parameters used by the function
(mu, sigma) = norm.fit(train['SalePrice'])
print( '\n mu = {:.2f} and sigma = {:.2f}\n'.format(mu, sigma))

#Now plot the distribution
plt.legend(['Normal dist. ($\mu=$ {:.2f} and $\sigma=$ {:.2f} )'.format(mu, sigma)],
            loc='best')
plt.ylabel('Frequency')
plt.title('SalePrice distribution')

#Get also the QQ-plot
fig = plt.figure()
res = stats.probplot(train['SalePrice'], plot=plt)
plt.show()

訓練データとテストデータを結合 + 欠損値の確認

ntrain = train.shape[0]
ntest = test.shape[0]
y_train = train.SalePrice.values
all_data = pd.concat((train, test)).reset_index(drop=True)
all_data.drop(['SalePrice'], axis=1, inplace=True)
print("all_data size is : {}".format(all_data.shape))

all_data_na = (all_data.isnull().sum() / len(all_data)) * 100
all_data_na = all_data_na.drop(all_data_na[all_data_na == 0].index).sort_values(ascending=False)[:30]
missing_data = pd.DataFrame({'Missing Ratio' :all_data_na})
missing_data.head(20)

f, ax = plt.subplots(figsize=(15, 12))
plt.xticks(rotation='90')
sns.barplot(x=all_data_na.index, y=all_data_na)
plt.xlabel('Features', fontsize=15)
plt.ylabel('Percent of missing values', fontsize=15)
plt.title('Percent missing data by feature', fontsize=15)

SalePriceと他の特徴の関係を確認

#Correlation map to see how features are correlated with SalePrice
corrmat = train.corr()
plt.subplots(figsize=(12,9))
sns.heatmap(corrmat, vmax=0.9, square=True)

all_data["PoolQC"] = all_data["PoolQC"].fillna("None")
all_data["MiscFeature"] = all_data["MiscFeature"].fillna("None")
all_data["Alley"] = all_data["Alley"].fillna("None")
all_data["Fence"] = all_data["Fence"].fillna("None")
all_data["FireplaceQu"] = all_data["FireplaceQu"].fillna("None")

欠損値の補填

#Group by neighborhood and fill in missing value by the median LotFrontage of all the neighborhood
all_data["LotFrontage"] = all_data.groupby("Neighborhood")["LotFrontage"].transform(
    lambda x: x.fillna(x.median()))

for col in ('GarageType', 'GarageFinish', 'GarageQual', 'GarageCond'):
    all_data[col] = all_data[col].fillna('None')
for col in ('GarageYrBlt', 'GarageArea', 'GarageCars'):
    all_data[col] = all_data[col].fillna(0)
for col in ('BsmtFinSF1', 'BsmtFinSF2', 'BsmtUnfSF','TotalBsmtSF', 'BsmtFullBath', 'BsmtHalfBath'):
    all_data[col] = all_data[col].fillna(0)
for col in ('BsmtQual', 'BsmtCond', 'BsmtExposure', 'BsmtFinType1', 'BsmtFinType2'):
    all_data[col] = all_data[col].fillna('None')
all_data["MasVnrType"] = all_data["MasVnrType"].fillna("None")
all_data["MasVnrArea"] = all_data["MasVnrArea"].fillna(0)

all_data = all_data.drop(['Utilities'], axis=1)

## mode は最頻値を集計
all_data['MSZoning'] = all_data['MSZoning'].fillna(all_data['MSZoning'].mode()[0])

all_data["Functional"] = all_data["Functional"].fillna("Typ")
all_data['Electrical'] = all_data['Electrical'].fillna(all_data['Electrical'].mode()[0])

all_data['KitchenQual'] = all_data['KitchenQual'].fillna(all_data['KitchenQual'].mode()[0])

all_data['Exterior1st'] = all_data['Exterior1st'].fillna(all_data['Exterior1st'].mode()[0])
all_data['Exterior2nd'] = all_data['Exterior2nd'].fillna(all_data['Exterior2nd'].mode()[0])

all_data['SaleType'] = all_data['SaleType'].fillna(all_data['SaleType'].mode()[0])
all_data['MSSubClass'] = all_data['MSSubClass'].fillna("None")

#Check remaining missing values if any 
all_data_na = (all_data.isnull().sum() / len(all_data)) * 100
all_data_na = all_data_na.drop(all_data_na[all_data_na == 0].index).sort_values(ascending=False)
missing_data = pd.DataFrame({'Missing Ratio' :all_data_na})
missing_data.head()

カテゴリの数値を str 変換

#MSSubClass=The building class
all_data['MSSubClass'] = all_data['MSSubClass'].apply(str)


#Changing OverallCond into a categorical variable
all_data['OverallCond'] = all_data['OverallCond'].astype(str)


#Year and month sold are transformed into categorical features.
all_data['YrSold'] = all_data['YrSold'].astype(str)
all_data['MoSold'] = all_data['MoSold'].astype(str)

カテゴリ変数のラベルエンコーディング

from sklearn.preprocessing import LabelEncoder
cols = ('FireplaceQu', 'BsmtQual', 'BsmtCond', 'GarageQual', 'GarageCond', 
        'ExterQual', 'ExterCond','HeatingQC', 'PoolQC', 'KitchenQual', 'BsmtFinType1', 
        'BsmtFinType2', 'Functional', 'Fence', 'BsmtExposure', 'GarageFinish', 'LandSlope',
        'LotShape', 'PavedDrive', 'Street', 'Alley', 'CentralAir', 'MSSubClass', 'OverallCond', 
        'YrSold', 'MoSold')
# process columns, apply LabelEncoder to categorical features
for c in cols:
    lbl = LabelEncoder() 
    lbl.fit(list(all_data[c].values)) 
    all_data[c] = lbl.transform(list(all_data[c].values))

# shape        
print('Shape all_data: {}'.format(all_data.shape))

# Adding total sqfootage feature 
all_data['TotalSF'] = all_data['TotalBsmtSF'] + all_data['1stFlrSF'] + all_data['2ndFlrSF']

ナンバー変数の歪度を確認

  • 歪度の絶対値が0.75以上であれば、boxcox1p変換
numeric_feats = all_data.dtypes[all_data.dtypes != "object"].index

# Check the skew of all numerical features
skewed_feats = all_data[numeric_feats].apply(lambda x: skew(x.dropna())).sort_values(ascending=False)
print("\nSkew in numerical features: \n")
skewness = pd.DataFrame({'Skew' :skewed_feats})
skewness.head(10)

skewness = skewness[abs(skewness) > 0.75]
print("There are {} skewed numerical features to Box Cox transform".format(skewness.shape[0]))

from scipy.special import boxcox1p
skewed_features = skewness.index
lam = 0.15
for feat in skewed_features:
    #all_data[feat] += 1
    all_data[feat] = boxcox1p(all_data[feat], lam)
    
#all_data[skewed_features] = np.log1p(all_data[skewed_features])

カテゴリ変数をダミー変数に変換

all_data = pd.get_dummies(all_data)
print(all_data.shape)

前処理完了

train = all_data[:ntrain]
test = all_data[ntrain:]

モデル作成

## RobustScaler: 中央値と四分位数を用いて変換(外れ値を無視)。
lasso = make_pipeline(RobustScaler(), Lasso(alpha =0.0005, random_state=1))

ENet = make_pipeline(RobustScaler(), ElasticNet(alpha=0.0005, l1_ratio=.9, random_state=3))
KRR = KernelRidge(alpha=0.6, kernel='polynomial', degree=2, coef0=2.5)
GBoost = GradientBoostingRegressor(n_estimators=3000, learning_rate=0.05,
                                   max_depth=4, max_features='sqrt',
                                   min_samples_leaf=15, min_samples_split=10, 
                                   loss='huber', random_state =5)
model_xgb = xgb.XGBRegressor(colsample_bytree=0.4603, gamma=0.0468, 
                             learning_rate=0.05, max_depth=3, 
                             min_child_weight=1.7817, n_estimators=2200,
                             reg_alpha=0.4640, reg_lambda=0.8571,
                             subsample=0.5213, silent=1,
                             random_state =7, nthread = -1)
model_lgb = lgb.LGBMRegressor(objective='regression',num_leaves=5,
                              learning_rate=0.05, n_estimators=720,
                              max_bin = 55, bagging_fraction = 0.8,
                              bagging_freq = 5, feature_fraction = 0.2319,
                              feature_fraction_seed=9, bagging_seed=9,
                              min_data_in_leaf =6, min_sum_hessian_in_leaf = 11)

モデル評価

#Validation function
n_folds = 5

def rmsle_cv(model):
    kf = KFold(n_folds, shuffle=True, random_state=42).get_n_splits(train.values)
    print('kf:', kf)
    rmse= np.sqrt(-cross_val_score(model, train.values, y_train, scoring="neg_mean_squared_error", cv = kf))
    return(rmse)

score = rmsle_cv(lasso)
print("\nLasso score: {:.4f} ({:.4f})\n".format(score.mean(), score.std()))

score = rmsle_cv(ENet)
print("ElasticNet score: {:.4f} ({:.4f})\n".format(score.mean(), score.std()))

score = rmsle_cv(KRR)
print("Kernel Ridge score: {:.4f} ({:.4f})\n".format(score.mean(), score.std()))

score = rmsle_cv(GBoost)
print("Gradient Boosting score: {:.4f} ({:.4f})\n".format(score.mean(), score.std()))

score = rmsle_cv(model_xgb)
print("Xgboost score: {:.4f} ({:.4f})\n".format(score.mean(), score.std()))

score = rmsle_cv(model_lgb)
print("LGBM score: {:.4f} ({:.4f})\n" .format(score.mean(), score.std()))

アンサンブル

  • Averaged Base Model
class AveragingModels(BaseEstimator, RegressorMixin, TransformerMixin):
    def __init__(self, models):
        self.models = models
        
    # we define clones of the original models to fit the data in
    def fit(self, X, y):
        self.models_ = [clone(x) for x in self.models]
        
        # Train cloned base models
        for model in self.models_:
            model.fit(X, y)

        return self
    
    #Now we do the predictions for cloned models and average them
    def predict(self, X):
        predictions = np.column_stack([
            model.predict(X) for model in self.models_
        ])
        return np.mean(predictions, axis=1)

averaged_models = AveragingModels(models = (ENet, GBoost, KRR, lasso))

score = rmsle_cv(averaged_models)
print(" Averaged base models score: {:.4f} ({:.4f})\n".format(score.mean(), score.std()))
  • Stacking Averaged Model
class StackingAveragedModels(BaseEstimator, RegressorMixin, TransformerMixin):
    def __init__(self, base_models, meta_model, n_folds=5):
        self.base_models = base_models
        self.meta_model = meta_model
        self.n_folds = n_folds
   
    # We again fit the data on clones of the original models
    def fit(self, X, y):
        self.base_models_ = [list() for x in self.base_models]
        self.meta_model_ = clone(self.meta_model)
        kfold = KFold(n_splits=self.n_folds, shuffle=True, random_state=156)
        
        # Train cloned base models then create out-of-fold predictions
        # that are needed to train the cloned meta-model
        out_of_fold_predictions = np.zeros((X.shape[0], len(self.base_models)))
        for i, model in enumerate(self.base_models):
            for train_index, holdout_index in kfold.split(X, y):
                instance = clone(model)
                self.base_models_[i].append(instance)
                instance.fit(X[train_index], y[train_index])
                y_pred = instance.predict(X[holdout_index])
                out_of_fold_predictions[holdout_index, i] = y_pred
                
        # Now train the cloned  meta-model using the out-of-fold predictions as new feature
        self.meta_model_.fit(out_of_fold_predictions, y)
        return self
   
    #Do the predictions of all base models on the test data and use the averaged predictions as 
    #meta-features for the final prediction which is done by the meta-model
    def predict(self, X):
        meta_features = np.column_stack([
            np.column_stack([model.predict(X) for model in base_models]).mean(axis=1)
            for base_models in self.base_models_ ])
        return self.meta_model_.predict(meta_features)

stacked_averaged_models = StackingAveragedModels(base_models = (ENet, GBoost, KRR),
                                                 meta_model = lasso)

score = rmsle_cv(stacked_averaged_models)
print("Stacking Averaged models score: {:.4f} ({:.4f})".format(score.mean(), score.std()))


def rmsle(y, y_pred):
    return np.sqrt(mean_squared_error(y, y_pred))

stacked_averaged_models.fit(train.values, y_train)
stacked_train_pred = stacked_averaged_models.predict(train.values)
stacked_pred = np.expm1(stacked_averaged_models.predict(test.values))
print(rmsle(y_train, stacked_train_pred))

model_xgb.fit(train, y_train)
xgb_train_pred = model_xgb.predict(train)
xgb_pred = np.expm1(model_xgb.predict(test))
print(rmsle(y_train, xgb_train_pred))


model_lgb.fit(train, y_train)
lgb_train_pred = model_lgb.predict(train)
lgb_pred = np.expm1(model_lgb.predict(test.values))
print(rmsle(y_train, lgb_train_pred))


'''RMSE on the entire Train data when averaging'''

print('RMSLE score on train data:')
print(rmsle(y_train,stacked_train_pred*0.70 +
               xgb_train_pred*0.15 + lgb_train_pred*0.15 ))

モデル予測

ensemble = stacked_pred*0.70 + xgb_pred*0.15 + lgb_pred*0.15

## 提出
sub = pd.DataFrame()
sub['Id'] = test_ID
sub['SalePrice'] = ensemble
sub.to_csv('submission.csv',index=False)

blog.kaggle.com

wc -l のアクセス集計

wc -l のアクセス集計 を pythonで集計した。

wc -l accesslog.*
a  = '''
    10914 accesslog.20180828010002
     8636 accesslog.20180829010001
     4742 accesslog.20180830010002
     6399 accesslog.20180831010001
     6901 accesslog.20180901010001
     5503 accesslog.20180902010001
     5988 accesslog.20180903010001
     7018 accesslog.20180904010002
     6500 accesslog.20180905010001
     6566 accesslog.20180906010001
     9494 accesslog.20180907010002
     6426 accesslog.20180908010001
     5942 accesslog.20180909010002
'''


b =[l.strip().split(' ') for l in a.strip().split('\n')]
df_b = pd.DataFrame(data=b, columns=['count','file'])

df_b['count'] = df_b['count'].astype(int)
df_b['date'] = df_b['file'].apply(lambda x: pd.to_datetime(x, format='accesslog.%Y%m%d%H%M%S', errors='ignore'))

fig = sns.mpl.pyplot.figure()
ax = fig.add_subplot(111)
ax.plot(list(df_b['date']), list(df_b['count']), label='access_count')
ax.axvline(x='2018-09-01', linewidth=2, color='r')
ax.legend()
fig.autofmt_xdate()
fig.savefig('access_count.png')
fig.show()

stackoverflow.com

MySQLのレプリケーションが遅延した場合

レプリケーション遅延

まずは、 show slave statusで Seconds_Behind_Master と Slave*Runningを確認する。
どれくらい遅延しているか確認できる。

slave1 [localhost] {msandbox} ((none)) > show slave status\G
*************************** 1. row ***************************
               Slave_IO_State: Waiting for master to send event
                  Master_Host: 127.0.0.1
                  Master_User: rsandbox
                  Master_Port: 19972
                Connect_Retry: 60
              Master_Log_File: mysql-bin.000003
          Read_Master_Log_Pos: 31122248
               Relay_Log_File: mysql_sandbox19973-relay-bin.000008
                Relay_Log_Pos: 30512168
        Relay_Master_Log_File: mysql-bin.000003
             Slave_IO_Running: Yes
            Slave_SQL_Running: Yes
              Replicate_Do_DB:
          Replicate_Ignore_DB:
           Replicate_Do_Table:
       Replicate_Ignore_Table:
      Replicate_Wild_Do_Table:
  Replicate_Wild_Ignore_Table:
                   Last_Errno: 0
                   Last_Error:
                 Skip_Counter: 0
          Exec_Master_Log_Pos: 30512022
              Relay_Log_Space: 31122709
              Until_Condition: None
               Until_Log_File:
                Until_Log_Pos: 0
           Master_SSL_Allowed: No
           Master_SSL_CA_File:
           Master_SSL_CA_Path:
              Master_SSL_Cert:
            Master_SSL_Cipher:
               Master_SSL_Key:
        Seconds_Behind_Master: 1
Master_SSL_Verify_Server_Cert: No
                Last_IO_Errno: 0
                Last_IO_Error:
               Last_SQL_Errno: 0
               Last_SQL_Error:
  Replicate_Ignore_Server_Ids:
             Master_Server_Id: 1
1 row in set (0.00 sec)

Slave_SQL_THREADが遅い場合は、以下のコマンドで、現在進行系の queryを確認

> show processlist\G;

nippondanji.blogspot.com

House Priceの分析5

前処理

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib

import matplotlib.pyplot as plt
from scipy.stats import skew
from scipy.stats.stats import pearsonr


%config InlineBackend.figure_format = 'retina' #set 'png' here when working on notebook
%matplotlib inline

train = pd.read_csv("kaggle/kaggle1/train.csv")
test = pd.read_csv("kaggle/kaggle1/train.csv")

## id 以外
all_data = pd.concat((train.loc[:,'MSSubClass':'SaleCondition'],
                      test.loc[:,'MSSubClass':'SaleCondition']))

## histgramで確認
matplotlib.rcParams['figure.figsize'] = (12.0, 6.0)
prices = pd.DataFrame({"price":train["SalePrice"], "log(price + 1)":np.log1p(train["SalePrice"])})
prices.hist()

train["SalePrice"] = np.log1p(train["SalePrice"])

#log transform skewed numeric features:
numeric_feats = all_data.dtypes[all_data.dtypes != "object"].index

# 歪度の高い特徴を pick up
skewed_feats = train[numeric_feats].apply(lambda x: skew(x.dropna())) #compute skewness
skewed_feats = skewed_feats[skewed_feats > 0.75]
skewed_feats = skewed_feats.index

all_data[skewed_feats] = np.log1p(all_data[skewed_feats])

all_data = pd.get_dummies(all_data)

#filling NA's with the mean of the column:
all_data = all_data.fillna(all_data.mean())

#creating matrices for sklearn:
X_train = all_data[:train.shape[0]]
X_test = all_data[train.shape[0]:]
y = train.SalePrice

from sklearn.linear_model import Ridge, RidgeCV, ElasticNet, LassoCV, LassoLarsCV
from sklearn.model_selection import cross_val_score

def rmse_cv(model):
    rmse= np.sqrt(-cross_val_score(model, X_train, y, scoring="neg_mean_squared_error", cv = 5))
    return(rmse)

model_ridge = Ridge()

リッジ回帰のベストパラメータ確認
alphas = [0.05, 0.1, 0.3, 1, 3, 5, 10, 15, 30, 50, 75]
cv_ridge = [rmse_cv(Ridge(alpha = alpha)).mean() 
            for alpha in alphas]

cv_ridge = pd.Series(cv_ridge, index = alphas)
cv_ridge.plot(title = "Validation - Just Do It")
plt.xlabel("alpha")
plt.ylabel("rmse")

# 最小値
cv_ridge.min()

# LASSO 回帰器
model_lasso = LassoCV(alphas = [1, 0.1, 0.001, 0.0005]).fit(X_train, y)

rmse_cv(model_lasso).mean()
coef = pd.Series(model_lasso.coef_, index = X_train.columns)

print("Lasso picked " + str(sum(coef != 0)) + " variables and eliminated the other " +  str(sum(coef == 0)) + " variables")

imp_coef = pd.concat([coef.sort_values().head(10),
                     coef.sort_values().tail(10)])

matplotlib.rcParams['figure.figsize'] = (8.0, 10.0)
imp_coef.plot(kind = "barh")
plt.title("Coefficients in the Lasso Model")

#let's look at the residuals as well:
matplotlib.rcParams['figure.figsize'] = (6.0, 6.0)

preds = pd.DataFrame({"preds":model_lasso.predict(X_train), "true":y})
preds["residuals"] = preds["true"] - preds["preds"]
preds.plot(x = "preds", y = "residuals",kind = "scatter")

xgboost modelを使用

import xgboost as xgb

dtrain = xgb.DMatrix(X_train, label = y)
dtest = xgb.DMatrix(X_test)

params = {"max_depth":2, "eta":0.1}
model = xgb.cv(params, dtrain,  num_boost_round=500, early_stopping_rounds=100)

model.loc[30:,["test-rmse-mean", "train-rmse-mean"]].plot()
model_xgb = xgb.XGBRegressor(n_estimators=360, max_depth=2, learning_rate=0.1) #the params were tuned using xgb.cv
model_xgb.fit(X_train, y)

xgb_preds = np.expm1(model_xgb.predict(X_test))
lasso_preds = np.expm1(model_lasso.predict(X_test))

## 予想と比較
predictions = pd.DataFrame({"xgb":xgb_preds, "lasso":lasso_preds})
predictions.plot(x = "xgb", y = "lasso", kind = "scatter")

Regularized Linear Models | Kaggle

MySQL から pandas.Dataframe へ読み込む

pandasから、mysqlに読み込む方法

import pandas as pd
import MySQLdb
 
def pd_dbread(table, columns_list):
    """ 接続サンプル """
 
    # 接続する 
    con = MySQLdb.connect(
            user='aaa',
            passwd='aaa',
            host='127.0.0.1',
            db='aaa',
             charset='utf8'
    )
 
    # カーソルを取得する
    cur= con.cursor()
     
    # クエリを実行する
    sql = """
    select {columns} from {table}
    """.format(
        columns=",".join(["`{}`".format(l) for l in columns_list]),
        table="`{}`".format(table)
    )
    df_read = pd.read_sql(sql, con,)
    con.close()
    return df_read


aaa_columns = [
            'id',
            'name',
        ]
table_name = "aaa"
df_aaa = pd_dbread(table_name, aaa_columns)

ramdom でshuffleすると、return Noneになる問題

こうすればいいらしい。

>>> import random
>>> x = ['foo', 'bar', 'black', 'sheep']
# O(N) operations・・・shuffle と同じロジック
>>> random.sample(x, len(x))
['bar', 'sheep', 'black', 'foo']
# O(NlogN) operation
>>> sorted(x, key=lambda k: random.random())
['sheep', 'foo', 'black', 'bar']
>>> x
['foo', 'bar', 'black', 'sheep']

stackoverflow.com

House Priceの分析4

XGBRegressorっていう、回帰モデルがあるので確認。 そもそも xgboost が結構界隈では有名らしい。

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import Imputer

data = pd.read_csv('kaggle/kaggle1/train.csv')
data.isnull().any(axis=0)

# Imputerは欠損値を mean(平均), median(中央値), mode(最頻値)のどれかに置き換える

data.dropna(axis=0, subset=['SalePrice'], inplace=True)
y = data.SalePrice
X = data.drop(['SalePrice'], axis=1).select_dtypes(exclude=['object'])

train_X, test_X, train_y, test_y = train_test_split(X.as_matrix(), y.as_matrix(), test_size=0.25)

my_imputer = Imputer()
train_X = my_imputer.fit_transform(train_X)
test_X = my_imputer.transform(test_X)

from xgboost import XGBRegressor

my_model = XGBRegressor()
# Add silent=True to avoid printing out updates with each cycle
my_model.fit(train_X, train_y, verbose=False)

# make predictions
predictions = my_model.predict(test_X)

from sklearn.metrics import mean_absolute_error
print("Mean Absolute Error : " + str(mean_absolute_error(predictions, test_y)))

my_model = XGBRegressor(n_estimators=1000)
my_model.fit(train_X, train_y, early_stopping_rounds=5, 
             eval_set=[(test_X, test_y)], verbose=False)

my_model = XGBRegressor(n_estimators=1000, learning_rate=0.05)
my_model.fit(train_X, train_y, early_stopping_rounds=5, 
             eval_set=[(test_X, test_y)], verbose=False)