大熊猫每月/每年的队列分析到季度

Question

我正在实施Greg Reda的队列分析（http://www.gregreda.com/2015/08/23/cohort-analysis-with-python/）。这种分析可以很容易地在每月和每年之间进行，但我不知道如何按季度实施。

他的完整代码

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl

pd.set_option('max_columns', 50)
mpl.rcParams['lines.linewidth'] = 2

%matplotlib inline
df = pd.read_excel('/Users/gjreda/Dropbox/datasets/relay-foods.xlsx')
df.head()

df['OrderPeriod'] = df.OrderDate.apply(lambda x: x.strftime('%Y-%m'))
df.head()

df.set_index('UserId', inplace=True)

df['CohortGroup'] = df.groupby(level=0)['OrderDate'].min().apply(lambda x:                     x.strftime('%Y-%m'))
df.reset_index(inplace=True)
df.head()

grouped = df.groupby(['CohortGroup', 'OrderPeriod'])

# count the unique users, orders, and total revenue per Group + Period
cohorts = grouped.agg({'UserId': pd.Series.nunique,
                       'OrderId': pd.Series.nunique,
                       'TotalCharges': np.sum})

# make the column names more meaningful
cohorts.rename(columns={'UserId': 'TotalUsers',
                        'OrderId': 'TotalOrders'}, inplace=True)
cohorts.head()

def cohort_period(df):
    """
    Creates a `CohortPeriod` column, which is the Nth period based on the     user's first purchase.

    Example
    -------
    Say you want to get the 3rd month for every user:
        df.sort(['UserId', 'OrderTime', inplace=True)
        df = df.groupby('UserId').apply(cohort_period)
        df[df.CohortPeriod == 3]
    """
    df['CohortPeriod'] = np.arange(len(df)) + 1
    return df

cohorts = cohorts.groupby(level=0).apply(cohort_period)
cohorts.head()

# reindex the DataFrame
cohorts.reset_index(inplace=True)
cohorts.set_index(['CohortGroup', 'CohortPeriod'], inplace=True)

# create a Series holding the total size of each CohortGroup
cohort_group_size = cohorts['TotalUsers'].groupby(level=0).first()
cohort_group_size.head()

user_retention = cohorts['TotalUsers'].unstack(0).divide(cohort_group_size,     axis=1)
user_retention.head(10)

user_retention[['2009-06', '2009-07', '2009-08']].plot(figsize=(10,5))
plt.title('Cohorts: User Retention')
plt.xticks(np.arange(1, 12.1, 1))
plt.xlim(1, 12)
plt.ylabel('% of Cohort Purchasing');

# Creating heatmaps in matplotlib is more difficult than it should be.
# Thankfully, Seaborn makes them easy for us.
# http://stanford.edu/~mwaskom/software/seaborn/

import seaborn as sns
sns.set(style='white')

plt.figure(figsize=(12, 8))
plt.title('Cohorts: User Retention')
sns.heatmap(user_retention.T, mask=user_retention.T.isnull(), annot=True,     fmt='.0%');

谢谢，

Answer 1

一种方法是修改现有代码的两行，将周期定义为四分之一：

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl

pd.set_option('max_columns', 50)
mpl.rcParams['lines.linewidth'] = 2

%matplotlib inline
df = pd.read_excel('chapter-12-relay-foods.xlsx',sheetname='Purchase Data - Full Study')
df.head()

将此行更改为按季度组织：

df['OrderPeriod'] = df.OrderDate.apply(lambda x: str(x.year)+'q'+str(x.quarter))
df

df.set_index('UserId', inplace=True)

df['CohortGroup'] = df.groupby(level=0)['OrderDate'].min().apply(lambda x:                     x.strftime('%Y-%m'))
df.reset_index(inplace=True)
df.head()

grouped = df.groupby(['CohortGroup', 'OrderPeriod'])

# count the unique users, orders, and total revenue per Group + Period
cohorts = grouped.agg({'UserId': pd.Series.nunique,
                       'OrderId': pd.Series.nunique,
                       'TotalCharges': np.sum})

# make the column names more meaningful
cohorts.rename(columns={'UserId': 'TotalUsers',
                        'OrderId': 'TotalOrders'}, inplace=True)
cohorts.head()

def cohort_period(df):
    """
    Creates a `CohortPeriod` column, which is the Nth period based on the     user's first purchase.

    Example
    -------
    Say you want to get the 3rd month for every user:
        df.sort(['UserId', 'OrderTime', inplace=True)
        df = df.groupby('UserId').apply(cohort_period)
        df[df.CohortPeriod == 3]
    """
    df['CohortPeriod'] = np.arange(len(df)) + 1
    return df

cohorts = cohorts.groupby(level=0).apply(cohort_period)
cohorts.head()

# reindex the DataFrame
cohorts.reset_index(inplace=True)
cohorts.set_index(['CohortGroup', 'CohortPeriod'], inplace=True)

# create a Series holding the total size of each CohortGroup
cohort_group_size = cohorts['TotalUsers'].groupby(level=0).first()
cohort_group_size.head()

user_retention = cohorts['TotalUsers'].unstack(0).divide(cohort_group_size,     axis=1)
user_retention.head(10)

user_retention[['2009-06', '2009-07', '2009-08']].plot(figsize=(10,5))
plt.title('Cohorts: User Retention')
plt.xticks(np.arange(1, 12.1, 1))

并将此更改为正确的x轴4个季度与12个月相比。

plt.xlim(1, 4)
plt.ylabel('% of Cohort Purchasing');

# Creating heatmaps in matplotlib is more difficult than it should be.
# Thankfully, Seaborn makes them easy for us.
# http://stanford.edu/~mwaskom/software/seaborn/

import seaborn as sns
sns.set(style='white')

plt.figure(figsize=(12, 8))
plt.title('Cohorts: User Retention')
sns.heatmap(user_retention.T, mask=user_retention.T.isnull(), annot=True,     fmt='.0%');