import pandas as pd
test_df = pd.read_csv("./test.csv")
test_df = pd.read_csv(names=['a_from_lng','a_from_lat','b_from_lng','b_from_lat',],skiprows=10)
test_df.columns
test_df['a_from_lng']
test_df['a_from_lng'].head()
test_df['a_from_lng'].head(100)
test_df['a_from_lng'].tail()
test_df['a_from_lng'].tail(100)
test_df.describe()
test_df['a_from_lng'].describe()
def distance(x1, y1, x2, y2):
return np.sqrt((x1-x2)**2+(y1-y2)**2)
test_df['start_distance_gap'] = map(lambda x1, y1, x2, y2: distance(x1, y1, x2, y2), \
test_df['a_from_lng'], test_df['a_from_lat'], test_df['b_from_lng'], test_df['b_from_lat'])
# 增加小时和分钟特征
a_setup_time = pd.DatetimeIndex(test_df['a_setup_time'])
test_df["a_setup_hour"] = pd.Index(a_setup_time).hour
test_df["a_setup_minute"] = pd.Index(a_setup_time).minute
test_df.drop('b_time', axis=1, inplace=True)
test_df.to_csv('./feature.csv')
test_df.to_csv('./feature.csv', columns=[0, 1, 2, 3], header=False)
useful_order_count = [balabala...]
test_df["useful"] = pd.Series(useful_order_count) # 在dataframe中增加新列useful,这个数据之前是一个list
- DataFrame 转换成 array 或 list
test_np = np.array(test_df) # np.ndarray()
test_list = test_np.tolist() # list
test_df['id'].value_counts()