Please note, this is a STATIC archive of website www.tutorialspoint.com from 11 May 2019, cach3.com does not collect or store any user information, there is no "phishing" involved.
# =============================================================================
# Adding predicitve variables
# =============================================================================
''' Adding age '''
# Reference date
reference_date = datetime.date(2017, 5, 1)
# Add age to the basetable
basetable["age"] = (pd.Series([calculate_age(date_of_birth, reference_date)
for date_of_birth in basetable["date_of_birth"]]))
# Calculate mean age
print(round(basetable["age"].mean()))
''' Adding the donor segment '''
# basetable
'''
donor_id
0 98304
1 4
2 32778
... ...
9488 65524
9489 98293
9490 32759
'''
# segments
'''
donor_id segment
1379 69844 silver
1191 36363 gold
681 67425 bronze
... ... ...
9153 97124 silver
6847 56218 silver
6134 53780 silver
'''
# Add the donor segment to the basetable
# Left join（right join 就只有交集，沒有 NaN）
basetable = pd.merge(basetable, segments, on =["donor_id"], how="left")
'''
donor_id segment
0 98304 NaN
1 4 NaN
2 32778 bronze
... ... ...
9488 65524 gold
9489 98293 silver
9490 32759 NaN
'''
# Count the number of donors in each segment
basetable.groupby("segment").size()
# Count the number of donors with no segment assigned
print(basetable["segment"].isna().sum())
''' Adding living place '''
# living_places
'''
donor_ID start_date end_date living_place
0 32768 1989-03-25 2000-07-06 India
1 32768 2000-07-06 2099-01-01 UK
2 98305 1954-04-06 1958-08-12 USA
... ... ... ... ...
28803 32765 1998-03-09 2005-01-30 UK
28804 32765 2005-01-30 2012-11-28 UK
28805 32765 2012-11-28 2099-01-01 India
'''
# Reference date
reference_date = datetime.date(2017, 5, 1)
# Select living place reference date
living_places_reference_date = living_places[(living_places["start_date"] <= reference_date) &
(living_places["end_date"] > reference_date)]
# Add living place to the basetable
basetable = pd.merge(basetable, living_places_reference_date[["donor_ID", "living_place"]], on="donor_ID")
# =============================================================================
# Adding aggregated variables
# =============================================================================
''' Maximum value last year '''
# basetable
'''
donor_ID
0 3
1 5
2 6
'''
# gifts
'''
id date amount
0 1 2015-10-16 75.0
1 1 2014-02-11 111.0
2 1 2012-03-28 93.0
'''
# Start and end date of the aggregation period
start_date = datetime.date(2017, 1, 1)
end_date = datetime.date(2017, 5, 1)
# Select gifts made in 2017 and before May 1st
gifts_2017 = gifts[(gifts["date"] >= start_date) & (gifts["date"] < end_date)]
# Maximum gift per donor in 2017
gifts_2017_bydonor = gifts_2017.groupby(["id"])["amount"].max().reset_index()
gifts_2017_bydonor.columns = ["donor_ID", "max_amount"]
# Add maximum amount to the basetable
basetable = pd.merge(basetable, gifts_2017_bydonor)
''' Recency of donations '''
# Reference date to calculate the recency
reference_date = datetime.date(2017, 5, 1)
# Select gifts made before the reference date
gifts_before_reference = gifts[(gifts["date"] < reference_date)]
# Latest gift per donor in 2017
last_gift = gifts_before_reference.groupby(["id"])["date"].max().reset_index()
last_gift["recency"] = reference_date - last_gift["date"]
# Add recency to the basetable
basetable = pd.merge(basetable, last_gift[["id", "recency"]], how="left")
print(basetable)
'''
id recency
0 3 396 days
1 5 291 days
2 6 414 days
... ... ...
8508 29983 NaT
8509 29986 NaT
8510 29991 NaT
'''
# =============================================================================
# Adding evolutions
# =============================================================================
''' Ratio of last month's and last year's average '''
# Given are gifts_last_month (donors who donated last month) and gifts_last_year (donors who donated last year)
# Average gift last month for each donor
average_gift_last_month = gifts_last_month.groupby("id")["amount"].mean().reset_index()
average_gift_last_month.columns = ["donor_ID", "mean_gift_last_month"]
# Average gift last year for each donor
average_gift_last_year = gifts_last_year.groupby("id")["amount"].mean().reset_index()
average_gift_last_year.columns = ["donor_ID", "mean_gift_last_year"]
# Add average gift last month and year to basetable
basetable = pd.merge(basetable, average_gift_last_month, on="donor_ID", how="left")
basetable = pd.merge(basetable, average_gift_last_year, on="donor_ID", how="left")
# Calculate ratio of last month's and last year's average
basetable["ratio_month_year"] = basetable["mean_gift_last_month"] / basetable["mean_gift_last_year"]
''' Absolute difference between two years '''
# Number of gifts in 2016 and 2017 for each donor
gifts_2016_bydonor = gifts_2016.groupby("id")["amount"].count().reset_index()
gifts_2016_bydonor.columns = ["donor_ID", "donations_2016"]
gifts_2017_bydonor = gifts_2017.groupby("id")["amount"].count().reset_index()
gifts_2017_bydonor.columns = ["donor_ID", "donations_2017"]
# Add number of gifts in 2016 and 2017 to the basetable
basetable = pd.merge(basetable, gifts_2016_bydonor, on="donor_ID", how="left")
basetable = pd.merge(basetable, gifts_2017_bydonor, on="donor_ID", how="left")
# Calculate the number of gifts in 2017 minus number of gifts in 2016
basetable.fillna(0)
basetable["gifts_2017_min_2016"] = basetable["donations_2017"] - basetable["donations_2016"]
print(basetable.head())
# =============================================================================
# Using evolution variables
# =============================================================================
''' Performance of evolution variables '''
# variables_regular = ["gender_F", "age", "donations_2017"]
# variables_evolution = ["gender_F", "age", "donations_2017_min_2016"]
# Select the evolution variables and fit the model
X_evolution = basetable[variables_evolution]
logreg.fit(X_evolution, y)
# Make predictions and calculate the AUC
predictions_evolution = logreg.predict_proba(X_evolution)[:,1]
auc_evolution = roc_auc_score(y, predictions_evolution)
# Print the respective AUC values（假設 auc_regular 已經算好了）
print(round(auc_regular, 2)) # 0.6
print(round(auc_evolution, 2)) # 0.7
''' Meaning of evolution: plot the pig table '''
# Discretize the variable in 5 bins and add to the basetable
basetable["donations_2017_min_2016_disc"] = pd.qcut(basetable["donations_2017_min_2016"], 5)
# Construct the predictor insight graph table
pig_table = create_pig_table(basetable, "target", "donations_2017_min_2016_disc")
# Plot the predictor insight graph
plot_pig(pig_table, "donations_2017_min_2016_disc")
Advertisements
We use cookies to provide and improve our services. By using our site, you consent to our Cookies Policy.
AcceptLearn more
