python 分析数据及预处理用到的函数

train = pd.read_csv("../input/train.csv")

test = pd.read_csv("../input/test.csv")

train.describe(include="all")   //#查看数值型数据情况：

train.describe()    #查看字符型数据情况：

train.describe(include=['0'])     

pd.set_option('display.max_columns', None)  #显示所有列，解决输出的结果特别会在最后输出时用......代替的情况:

train.info()

train.head()  #总体预览

 

#查找NAN超过1000的列并删除
columns = [col for col in df.columns if df[col].isnull().sum() > 1000]
df = df.drop(columns, axis=1)

# 用平均值填充LotFrontage列的空值
df['LotFrontage'].fillna((df['LotFrontage'].mean()), inplace=True)

# No garage values means no year, area or cars
for col in ['GarageYrBlt', 'GarageArea', 'GarageCars']:
    df[col] = df[col].fillna(0)

# No garage info means you don't have one
for col in ['GarageType', 'GarageFinish', 'GarageQual', 'GarageCond']:
    df[col] = df[col].fillna('None')

# Fill no basement
for col in ['BsmtQual', 'BsmtCond', 'BsmtExposure', 'BsmtFinType1', 'BsmtFinType2']:
    df[col] = df[col].fillna('None')

# Fill remaining categorical and numerical cols with None and 0
cat_columns = df.select_dtypes('object').columns
num_columns = [i for i in list(df.columns) if i not in cat_columns]
df.update(df[cat_columns].fillna('None'))
df.update(df[num_columns].fillna(0))

# 用于检查是否含有空值  不含有则输出false，否则true
print(df.isnull().values.any())