pandas技巧2

# 方法1
def get_counts(sequence):
    counts = {}  # 将计数值保存在字典中
    for x in sequence:
        if x in counts:
            counts[x] += 1   # 存在则计数加1
        else:
            counts[x] = 1    # 不存在则定为1
    return counts


# 方法2
from collections import defaultdict

def get_counts2(sequence):
  counts = defaultdict(int)
  for x in sequence:
    counts[x] += 1
  return counts

# 标准化过程：使用自定义的标准化函数实现
def normal_total(group):
    group['normed_total'] = group.total / group.total.sum()
    return group

# 按照性别计算平均得分
mean_ratings = data.pivot_table('rating',   # 得分
                                index='title',  # 行索引index
                                columns='gender', # 列属性gender
                                aggfunc='mean')  # 使用的函数：平均分
mean_ratings[:5]

!head -n 10 /Users/peter/data-visualization/pydata-book/datasets/babynames/yob1880.txt
# 查看某个文件的前10行数据