输入 [ ]
已复制！
# pip install ydf temporian -U
# pip install ydf temporian -U
输入 [8]
已复制！
import ydf
import temporian as tp
import pandas as pd
import datetime
import os
import ydf import temporian as tp import pandas as pd import datetime import os
什么是时间序列？¶
时间序列或事件序列是带有特征数据的、非均匀采样的带时间戳的事件。这类数据有许多示例：银行交易日志、销售日志、网络日志、患者测量数据、治疗日志等等。决策森林非常适合处理事件序列，因为预处理事件序列的输出是表格形式的，并且可能稀疏且包含噪声。
使用时间数据时，YDF 模型能从特征预处理中获益匪浅。基本操作可以使用 Pandas 等通用数据处理工具来处理。对于更复杂的用例，时间特征预处理工具非常有用。本教程演示如何将 YDF 与 Temporian 数据预处理库集成。
在本 Notebook 中，我们的目标是确定来自可复现的信用卡欺诈检测机器学习数据集的交易是否属于欺诈。每笔交易都是一个事件，包含金额、客户 ID 和终端 ID。我们的模型将考虑交易特征以及相关交易（例如，来自同一客户的交易和来自同一终端的交易）。为此，我们将对事件数据进行预处理，以便 YDF 模型可以检测欺诈。
注意：本教程是对使用 Temporian 和 TensorFlow 决策森林检测支付卡欺诈教程的简化改编。
注意 2： Yggdrasil Decision Forests 和 Temporian 共享部分开发团队。
下载数据集¶
交易数据以 CSV 格式提供，2018 年 4 月 1 日至 2018 年 9 月 30 日期间的每天一个文件。我们使用 2018 年 4 月 1 日至 2018 年 8 月 31 日（含）的交易数据进行训练，使用 2018 年 9 月 1 日至 2018 年 9 月 30 日的交易数据进行评估。
输入 [46]
已复制！
start_date = datetime.date(2018, 4, 1)
end_date = datetime.date(2018, 9, 30)
train_test_split = datetime.datetime(2018, 9, 1)
# List the input csv files
filenames = []
while start_date <= end_date:
filenames.append(f"{start_date}.pkl")
start_date += datetime.timedelta(days=1)
print(f"{len(filenames)} dates")
# Download and load files
print("Loading files (this step can take a minute)")
def load_date(idx_and_filename):
if (idx_and_filename[0]%10) == 0:
print(f"[{idx_and_filename[0]}/{len(filenames)}]", end="", flush=True)
return pd.read_pickle(f"https://github.com/Fraud-Detection-Handbook/simulated-data-raw/raw/main/data/{idx_and_filename[1]}")
transactions_pd = pd.concat(map(load_date, enumerate(filenames)))
print("Done!")
print(f"Found {len(transactions_pd)} transactions")
start_date = datetime.date(2018, 4, 1) end_date = datetime.date(2018, 9, 30) train_test_split = datetime.datetime(2018, 9, 1) # List the input csv files filenames = [] while start_date <= end_date: filenames.append(f"{start_date}.pkl") start_date += datetime.timedelta(days=1) print(f"{len(filenames)} dates") # Download and load files print("Loading files (this step can take a minute)") def load_date(idx_and_filename): if (idx_and_filename[0]%10) == 0: print(f"[{idx_and_filename[0]}/{len(filenames)}]", end="", flush=True) return pd.read_pickle(f"https://github.com/Fraud-Detection-Handbook/simulated-data-raw/raw/main/data/{idx_and_filename[1]}") transactions_pd = pd.concat(map(load_date, enumerate(filenames))) print("Done!") print(f"Found {len(transactions_pd)} transactions")
183 dates Loading files (this step can take a minute) [0/183][10/183][20/183][30/183][40/183][50/183][60/183][70/183][80/183][90/183][100/183][110/183][120/183][130/183][140/183][150/183][160/183][170/183][180/183]Done! Found 1754155 transactions
输入 [57]
已复制！
transactions_pd
transactions_pd
输出 [57]
| TRANSACTION_ID | TX_DATETIME | CUSTOMER_ID | TERMINAL_ID | TX_AMOUNT | TX_TIME_SECONDS | TX_TIME_DAYS | TX_FRAUD | TX_FRAUD_SCENARIO | |
|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 2018-04-01 00:00:31 | 596 | 3156 | 57.16 | 31 | 0 | 0 | 0 |
| 1 | 1 | 2018-04-01 00:02:10 | 4961 | 3412 | 81.51 | 130 | 0 | 0 | 0 |
| 2 | 2 | 2018-04-01 00:07:56 | 2 | 1365 | 146.00 | 476 | 0 | 0 | 0 |
| 3 | 3 | 2018-04-01 00:09:29 | 4128 | 8737 | 64.49 | 569 | 0 | 0 | 0 |
| 4 | 4 | 2018-04-01 00:10:34 | 927 | 9906 | 50.99 | 634 | 0 | 0 | 0 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 1754150 | 1754150 | 2018-09-30 23:56:36 | 161 | 655 | 54.24 | 15810996 | 182 | 0 | 0 |
| 1754151 | 1754151 | 2018-09-30 23:57:38 | 4342 | 6181 | 1.23 | 15811058 | 182 | 0 | 0 |
| 1754152 | 1754152 | 2018-09-30 23:58:21 | 618 | 1502 | 6.62 | 15811101 | 182 | 0 | 0 |
| 1754153 | 1754153 | 2018-09-30 23:59:52 | 4056 | 3067 | 55.40 | 15811192 | 182 | 0 | 0 |
| 1754154 | 1754154 | 2018-09-30 23:59:57 | 3542 | 9849 | 23.59 | 15811197 | 182 | 0 | 0 |
1754155 行 × 9 列
TX_FRAUD 表示交易是否为欺诈。这是标签。
准备数据¶
我们现在的数据存储在Pandas DataFrame中。我们想将其转换为 Temporian EventSet，以便进行预处理。
输入 [58]
已复制！
transactions_es = tp.from_pandas(
transactions_pd[["TX_DATETIME", "CUSTOMER_ID", "TERMINAL_ID",
"TX_AMOUNT", "TX_FRAUD"]],
timestamps="TX_DATETIME")
transactions_es
transactions_es = tp.from_pandas( transactions_pd[["TX_DATETIME", "CUSTOMER_ID", "TERMINAL_ID", "TX_AMOUNT", "TX_FRAUD"]], timestamps="TX_DATETIME") transactions_es
WARNING:root:Feature "CUSTOMER_ID" is an array of numpy.object_ and will be casted to numpy.string_ (Note: numpy.string_ is equivalent to numpy.bytes_). WARNING:root:Feature "TERMINAL_ID" is an array of numpy.object_ and will be casted to numpy.string_ (Note: numpy.string_ is equivalent to numpy.bytes_).
输出 [58]
特征 [4]: CUSTOMER_ID (str_) , TERMINAL_ID (str_) , TX_AMOUNT (float64) , TX_FRAUD (int64)
索引 [0]: 无
事件: 1754155
索引值: 1
内存使用: 56.1 MB
索引 ( ) 包含 1754155 个事件
| timestamp | CUSTOMER_ID | TERMINAL_ID | TX_AMOUNT | TX_FRAUD |
|---|---|---|---|---|
| 2018-04-01 00:00:31+00:00 | 596 | 3156 | 57.16 | 0 |
| 2018-04-01 00:02:10+00:00 | 4961 | 3412 | 81.51 | 0 |
| 2018-04-01 00:07:56+00:00 | 2 | 1365 | 146 | 0 |
| 2018-04-01 00:09:29+00:00 | 4128 | 8737 | 64.49 | 0 |
| 2018-04-01 00:10:34+00:00 | 927 | 9906 | 50.99 | 0 |
| … | … | … | … | … |
我们来绘制 CUSTOMER_ID=3774 的交易图。我们可以看到一些欺诈行为。
输入 [59]
已复制！
transactions_es.filter(tp.equal(transactions_es["CUSTOMER_ID"],"3774")).plot()
transactions_es.filter(tp.equal(transactions_es["CUSTOMER_ID"],"3774")).plot()
在此数据集中，确定交易是否为欺诈需要一周时间。对于每笔交易，我们将计算过去 1 到 4 周内同一终端发生的欺诈交易数量。我们还将计算该终端在过去一天、一周和四周内的交易数量以及交易总金额。最后，我们将提取每笔交易的当天小时数和星期几。
输入 [61]
已复制！
# @tp.compile # Uncomment tp.compile to run faster
def extract_features(transactions: tp.types.EventSetOrNode) -> dict[str, tp.types.EventSetOrNode]:
per_terminal_features = []
# Index the transactions per customer
per_terminal = transactions.add_index("TERMINAL_ID")
# 1. NUM PREVIOUS FRAUDS
# Lag the frauds by 1 week
lagged_fraud_per_terminal = per_terminal["TX_FRAUD"].lag(tp.duration.weeks(1))
# Moving sum of transactions over the last 4 weeks
per_terminal_features.append(
lagged_fraud_per_terminal
.moving_sum(tp.duration.weeks(4), sampling=per_terminal)
.rename("per_terminal.moving_sum_frauds"))
# 2. NUM PAST TRANSACTIONS AND AMOUNT
for day in [1, 7, 4*7]:
per_terminal_features.append(
per_terminal
.moving_count(tp.duration.days(day))
.rename(f"per_terminal.moving_count_transaction_{day}d"))
per_terminal_features.append(
per_terminal["TX_AMOUNT"]
.moving_sum(tp.duration.days(day))
.rename(f"per_terminal.moving_sum_transaction_{day}d"))
# 3. CALENDAR FEATURES
# Hour of day and day of week of each transaction.
per_terminal_features.append(per_terminal.calendar_hour())
per_terminal_features.append(per_terminal.calendar_day_of_week())
# Aggregate the raw data and features
return tp.glue(
per_terminal,
*per_terminal_features).drop_index("TERMINAL_ID")
feature_transactions_es = extract_features(transactions_es)
feature_transactions_es
# @tp.compile # 取消注释 tp.compile 以运行更快 def extract_features(transactions: tp.types.EventSetOrNode) -> dict[str, tp.types.EventSetOrNode]: per_terminal_features = [] # 按客户索引交易 per_terminal = transactions.add_index("TERMINAL_ID") # 1. 之前欺诈的数量 # 将欺诈滞后 1 周 lagged_fraud_per_terminal = per_terminal["TX_FRAUD"].lag(tp.duration.weeks(1)) # 过去 4 周的交易滚动总和 per_terminal_features.append( lagged_fraud_per_terminal .moving_sum(tp.duration.weeks(4), sampling=per_terminal) .rename("per_terminal.moving_sum_frauds")) # 2. 过去交易数量和金额 for day in [1, 7, 4*7]: per_terminal_features.append( per_terminal .moving_count(tp.duration.days(day)) .rename(f"per_terminal.moving_count_transaction_{day}d")) per_terminal_features.append( per_terminal["TX_AMOUNT"] .moving_sum(tp.duration.days(day)) .rename(f"per_terminal.moving_sum_transaction_{day}d")) # 3. 日历特征 # 每笔交易的小时和星期几。 per_terminal_features.append(per_terminal.calendar_hour()) per_terminal_features.append(per_terminal.calendar_day_of_week()) # 聚合原始数据和特征 return tp.glue( per_terminal, *per_terminal_features).drop_index("TERMINAL_ID") feature_transactions_es = extract_features(transactions_es) feature_transactions_es
输出 [61]
特征 [13]: CUSTOMER_ID (str_) , TX_AMOUNT (float64) , TX_FRAUD (int64) , per_terminal.moving_sum_frauds (int64) , per_terminal.moving_count_transaction_1d (int32) , per_terminal.moving_sum_transaction_1d (float64) , per_terminal.moving_count_transaction_7d (int32) , per_terminal.moving_sum_transaction_7d (float64) , per_terminal.moving_count_transaction_28d (int32) , per_terminal.moving_sum_transaction_28d (float64) , calendar_hour (int32) , calendar_day_of_week (int32) , TERMINAL_ID (str_)
索引 [0]: 无
事件: 1754155
索引值: 1
内存使用: 147.4 MB
索引 ( ) 包含 1754155 个事件
| timestamp | CUSTOMER_ID | TX_AMOUNT | TX_FRAUD | per_terminal.moving_sum_frauds | per_terminal.moving_count_transaction_1d | per_terminal.moving_sum_transaction_1d | per_terminal.moving_count_transaction_7d | per_terminal.moving_sum_transaction_7d | per_terminal.moving_count_transaction_28d | per_terminal.moving_sum_transaction_28d | calendar_hour | calendar_day_of_week | TERMINAL_ID |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2018-04-01 00:00:31+00:00 | 596 | 57.16 | 0 | 0 | 1 | 57.16 | 1 | 57.16 | 1 | 57.16 | 0 | 6 | 3156 |
| 2018-04-01 00:02:10+00:00 | 4961 | 81.51 | 0 | 0 | 1 | 81.51 | 1 | 81.51 | 1 | 81.51 | 0 | 6 | 3412 |
| 2018-04-01 00:07:56+00:00 | 2 | 146 | 0 | 0 | 1 | 146 | 1 | 146 | 1 | 146 | 0 | 6 | 1365 |
| 2018-04-01 00:09:29+00:00 | 4128 | 64.49 | 0 | 0 | 1 | 64.49 | 1 | 64.49 | 1 | 64.49 | 0 | 6 | 8737 |
| 2018-04-01 00:10:34+00:00 | 927 | 50.99 | 0 | 0 | 1 | 50.99 | 1 | 50.99 | 1 | 50.99 | 0 | 6 | 9906 |
| … | … | … | … | … | … | … | … | … | … | … | … | … | … |
我们为我们最喜欢的客户绘制特征图
输入 [62]
已复制！
feature_transactions_es.filter(tp.equal(feature_transactions_es["CUSTOMER_ID"],"3774")).plot()
feature_transactions_es.filter(tp.equal(feature_transactions_es["CUSTOMER_ID"],"3774")).plot()
训练和评估模型¶
我们将数据集分为训练集和测试集，将 Temporian EventSet 转换回 Pandas DataFrame，并训练一个 YDF 模型。
输入 [63]
已复制！
is_train = feature_transactions_es.timestamps() < train_test_split.timestamp()
is_test = ~is_train
train_feature_transactions_es = feature_transactions_es.filter(is_train)
test_feature_transactions_es = feature_transactions_es.filter(is_test)
print(f"{train_feature_transactions_es.num_events()} training transactions")
print(f"{test_feature_transactions_es.num_events()} testing transactions")
is_train = feature_transactions_es.timestamps() < train_test_split.timestamp() is_test = ~is_train train_feature_transactions_es = feature_transactions_es.filter(is_train) test_feature_transactions_es = feature_transactions_es.filter(is_test) print(f"{train_feature_transactions_es.num_events()} training transactions") print(f"{test_feature_transactions_es.num_events()} testing transactions")
1466091 training transactions 288064 testing transactions
输入 [64]
已复制！
train_ds_pd = tp.to_pandas(train_feature_transactions_es)
test_ds_pd = tp.to_pandas(test_feature_transactions_es)
print(f"{len(train_ds_pd)} training examples")
print(f"{len(test_ds_pd)} testing examples")
train_ds_pd = tp.to_pandas(train_feature_transactions_es) test_ds_pd = tp.to_pandas(test_feature_transactions_es) print(f"{len(train_ds_pd)} training examples") print(f"{len(test_ds_pd)} testing examples")
1466091 training examples 288064 testing examples
输入 [65]
已复制！
train_ds_pd
train_ds_pd
输出 [65]
| CUSTOMER_ID | TX_AMOUNT | TX_FRAUD | per_terminal.moving_sum_frauds | per_terminal.moving_count_transaction_1d | per_terminal.moving_sum_transaction_1d | per_terminal.moving_count_transaction_7d | per_terminal.moving_sum_transaction_7d | per_terminal.moving_count_transaction_28d | per_terminal.moving_sum_transaction_28d | calendar_hour | calendar_day_of_week | TERMINAL_ID | timestamp | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 596 | 57.16 | 0 | 0 | 1 | 57.16 | 1 | 57.16 | 1 | 57.16 | 0 | 6 | 3156 | 1.522541e+09 |
| 1 | 4961 | 81.51 | 0 | 0 | 1 | 81.51 | 1 | 81.51 | 1 | 81.51 | 0 | 6 | 3412 | 1.522541e+09 |
| 2 | 2 | 146.00 | 0 | 0 | 1 | 146.00 | 1 | 146.00 | 1 | 146.00 | 0 | 6 | 1365 | 1.522541e+09 |
| 3 | 4128 | 64.49 | 0 | 0 | 1 | 64.49 | 1 | 64.49 | 1 | 64.49 | 0 | 6 | 8737 | 1.522541e+09 |
| 4 | 927 | 50.99 | 0 | 0 | 1 | 50.99 | 1 | 50.99 | 1 | 50.99 | 0 | 6 | 9906 | 1.522541e+09 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 1466086 | 1321 | 79.06 | 0 | 0 | 2 | 123.09 | 8 | 342.55 | 26 | 941.59 | 21 | 4 | 229 | 1.535753e+09 |
| 1466087 | 4202 | 13.53 | 0 | 0 | 3 | 216.03 | 5 | 315.35 | 24 | 1233.40 | 21 | 4 | 5559 | 1.535753e+09 |
| 1466088 | 1879 | 19.64 | 0 | 0 | 1 | 19.64 | 7 | 274.47 | 26 | 1046.89 | 21 | 4 | 601 | 1.535753e+09 |
| 1466089 | 1864 | 73.29 | 0 | 0 | 4 | 192.22 | 13 | 598.69 | 25 | 1106.18 | 21 | 4 | 4571 | 1.535753e+09 |
| 1466090 | 409 | 56.21 | 0 | 0 | 2 | 145.79 | 8 | 568.48 | 33 | 1959.01 | 21 | 4 | 8457 | 1.535753e+09 |
1466091 行 × 14 列
输入 [66]
已复制！
learner = ydf.GradientBoostedTreesLearner(label="TX_FRAUD",
features=["per_terminal.moving_sum_frauds",
"per_terminal.moving_count_transaction_1d",
"per_terminal.moving_count_transaction_7d",
"per_terminal.moving_count_transaction_28d",
"calendar_hour",
"calendar_day_of_week",
],
num_trees=100, # Speed-up the training
)
model = learner.train(train_ds_pd)
learner = ydf.GradientBoostedTreesLearner(label="TX_FRAUD", features=["per_terminal.moving_sum_frauds", "per_terminal.moving_count_transaction_1d", "per_terminal.moving_count_transaction_7d", "per_terminal.moving_count_transaction_28d", "calendar_hour", "calendar_day_of_week", ], num_trees=100, # 加快训练速度 ) model = learner.train(train_ds_pd)
Train model on 1466091 examples Model trained in 0:00:40.887605
我们可以在测试数据集上评估模型。
理解模型¶
虽然模型不是直接操作原始交易数据，而是操作预处理后的特征，但模型是可以解释的。例如，通过检查变量重要性，我们可以看到特征 per_terminal.moving_sum_frauds 对模型来说最重要，而 calendar_day_of_week 则不太重要。我们可以将其解释为：如果客户过去曾有欺诈交易，那么这是未来欺诈交易的一个良好指标。
输入 [68]
已复制！
model.describe()
model.describe()
输出 [68]
名称 : GRADIENT_BOOSTED_TREES
任务 : CLASSIFICATION
标签 : TX_FRAUD
特征 (6) : per_terminal.moving_sum_frauds per_terminal.moving_count_transaction_1d per_terminal.moving_count_transaction_7d per_terminal.moving_count_transaction_28d calendar_hour calendar_day_of_week
权重 : 无
使用调优器训练 : 否
模型大小 : 1406 kB
任务 : CLASSIFICATION
标签 : TX_FRAUD
特征 (6) : per_terminal.moving_sum_frauds per_terminal.moving_count_transaction_1d per_terminal.moving_count_transaction_7d per_terminal.moving_count_transaction_28d calendar_hour calendar_day_of_week
权重 : 无
使用调优器训练 : 否
模型大小 : 1406 kB
Number of records: 1466091 Number of columns: 7 Number of columns by type: NUMERICAL: 6 (85.7143%) CATEGORICAL: 1 (14.2857%) Columns: NUMERICAL: 6 (85.7143%) 0: "per_terminal.moving_sum_frauds" NUMERICAL mean:0.197974 min:0 max:53 sd:1.59577 1: "per_terminal.moving_count_transaction_1d" NUMERICAL mean:1.99715 min:1 max:12 sd:1.02114 2: "per_terminal.moving_count_transaction_7d" NUMERICAL mean:7.84226 min:1 max:28 sd:3.1002 3: "per_terminal.moving_count_transaction_28d" NUMERICAL mean:26.4539 min:1 max:79 sd:9.81157 4: "calendar_hour" NUMERICAL mean:11.4991 min:0 max:23 sd:5.05594 5: "calendar_day_of_week" NUMERICAL mean:2.9861 min:0 max:6 sd:2.00096 CATEGORICAL: 1 (14.2857%) 6: "TX_FRAUD" CATEGORICAL has-dict vocab-size:3 zero-ood-items most-frequent:"0" 1453959 (99.1725%) Terminology: nas: Number of non-available (i.e. missing) values. ood: Out of dictionary. manually-defined: Attribute whose type is manually defined by the user, i.e., the type was not automatically inferred. tokenized: The attribute value is obtained through tokenization. has-dict: The attribute is attached to a string dictionary e.g. a categorical attribute stored as a string. vocab-size: Number of unique values.
以下评估是在验证集或袋外数据集上计算得出的。
Task: CLASSIFICATION
Label: TX_FRAUD
Loss (BINOMIAL_LOG_LIKELIHOOD): 0.0692174
Accuracy: 0.99269 CI95[W][0 1]
ErrorRate: : 0.00730968
Confusion Table:
truth\prediction
0 1
0 145251 236
1 836 332
Total: 146655
变量重要性衡量输入特征对模型的重要性。
1. "per_terminal.moving_sum_frauds" 0.900000 ################
2. "per_terminal.moving_count_transaction_28d" 0.290564 ##
3. "per_terminal.moving_count_transaction_7d" 0.215782
4. "calendar_hour" 0.190089
5. "calendar_day_of_week" 0.188707
6. "per_terminal.moving_count_transaction_1d" 0.180135
1. "per_terminal.moving_sum_frauds" 88.000000 ################
2. "per_terminal.moving_count_transaction_28d" 8.000000 #
3. "per_terminal.moving_count_transaction_7d" 2.000000
4. "calendar_day_of_week" 1.000000
1. "per_terminal.moving_count_transaction_28d" 859.000000 ################
2. "per_terminal.moving_sum_frauds" 824.000000 ###############
3. "per_terminal.moving_count_transaction_7d" 525.000000 ########
4. "calendar_hour" 306.000000 ###
5. "calendar_day_of_week" 214.000000 #
6. "per_terminal.moving_count_transaction_1d" 132.000000
1. "per_terminal.moving_sum_frauds" 2574.658942 ################
2. "per_terminal.moving_count_transaction_28d" 692.886033 ####
3. "per_terminal.moving_count_transaction_7d" 305.556677 #
4. "calendar_hour" 83.875978
5. "calendar_day_of_week" 79.349436
6. "per_terminal.moving_count_transaction_1d" 34.315195
这些变量重要性是在训练期间计算得出的。在测试数据集上分析模型时，可以获得更多（可能更有信息量）的变量重要性。
树数量 : 99
仅打印第一棵树。
Tree #0:
"per_terminal.moving_sum_frauds">=2.5 [s:0.00122566 n:1319436 np:10761 miss:0] ; pred:3.22407e-10
├─(pos)─ "per_terminal.moving_sum_frauds">=18.5 [s:0.0176001 n:10761 np:3536 miss:0] ; pred:4.68509
| ├─(pos)─ "per_terminal.moving_count_transaction_28d">=29.5 [s:0.00771428 n:3536 np:2178 miss:0] ; pred:2.38384
| | ├─(pos)─ "per_terminal.moving_sum_frauds">=24.5 [s:0.0209201 n:2178 np:1388 miss:0] ; pred:3.22545
| | | ├─(pos)─ "per_terminal.moving_count_transaction_28d">=37.5 [s:0.00556346 n:1388 np:633 miss:0] ; pred:1.90128
| | | | ├─(pos)─ pred:2.8898
| | | | └─(neg)─ pred:1.07249
| | | └─(neg)─ "per_terminal.moving_count_transaction_28d">=36.5 [s:0.0096319 n:790 np:206 miss:0] ; pred:5
| | | ├─(pos)─ pred:5
| | | └─(neg)─ pred:4.84463
| | └─(neg)─ "per_terminal.moving_sum_frauds">=22.5 [s:0.00322549 n:1358 np:543 miss:0] ; pred:1.03403
| | ├─(pos)─ "per_terminal.moving_sum_frauds">=23.5 [s:0.000536586 n:543 np:399 miss:0] ; pred:0.189689
| | | ├─(pos)─ pred:0.0208172
| | | └─(neg)─ pred:0.657606
| | └─(neg)─ "per_terminal.moving_count_transaction_28d">=25.5 [s:0.00624813 n:815 np:378 miss:1] ; pred:1.59659
| | ├─(pos)─ pred:2.62795
| | └─(neg)─ pred:0.704466
| └─(neg)─ "per_terminal.moving_sum_frauds">=3.5 [s:0.00906797 n:7225 np:6188 miss:0] ; pred:5
| ├─(pos)─ "per_terminal.moving_sum_frauds">=9.5 [s:0.0036483 n:6188 np:3617 miss:0] ; pred:5
| | ├─(pos)─ "per_terminal.moving_count_transaction_28d">=22.5 [s:0.0138705 n:3617 np:2748 miss:1] ; pred:5
| | | ├─(pos)─ pred:5
| | | └─(neg)─ pred:3.12495
| | └─(neg)─ "per_terminal.moving_count_transaction_28d">=27.5 [s:0.00442462 n:2571 np:1083 miss:0] ; pred:5
| | ├─(pos)─ pred:5
| | └─(neg)─ pred:5
| └─(neg)─ "per_terminal.moving_count_transaction_28d">=28.5 [s:0.0251879 n:1037 np:616 miss:0] ; pred:2.98852
| ├─(pos)─ "per_terminal.moving_count_transaction_28d">=47.5 [s:0.00377678 n:616 np:147 miss:0] ; pred:1.39635
| | ├─(pos)─ pred:0.0642654
| | └─(neg)─ pred:1.81387
| └─(neg)─ "per_terminal.moving_count_transaction_28d">=22.5 [s:0.0124898 n:421 np:251 miss:1] ; pred:5
| ├─(pos)─ pred:4.20204
| └─(neg)─ pred:5
└─(neg)─ "per_terminal.moving_sum_frauds">=1.5 [s:6.26323e-06 n:1308675 np:7935 miss:0] ; pred:-0.0385246
├─(pos)─ "per_terminal.moving_count_transaction_28d">=11.5 [s:0.000800429 n:7935 np:7915 miss:1] ; pred:0.350309
| ├─(pos)─ "per_terminal.moving_count_transaction_28d">=15.5 [s:0.000222715 n:7915 np:7832 miss:1] ; pred:0.333051
| | ├─(pos)─ "per_terminal.moving_count_transaction_28d">=33.5 [s:0.000176741 n:7832 np:2934 miss:0] ; pred:0.314408
| | | ├─(pos)─ pred:0.105963
| | | └─(neg)─ pred:0.43927
| | └─(neg)─ "per_terminal.moving_count_transaction_7d">=9.5 [s:0.0112688 n:83 np:5 miss:0] ; pred:2.09225
| | ├─(pos)─ pred:5
| | └─(neg)─ pred:1.7661
| └─(neg)─ "per_terminal.moving_count_transaction_28d">=9.5 [s:0.0533333 n:20 np:15 miss:1] ; pred:5
| ├─(pos)─ "calendar_hour">=13.5 [s:0.0355556 n:15 np:5 miss:0] ; pred:5
| | ├─(pos)─ pred:2.32618
| | └─(neg)─ pred:5
| └─(neg)─ pred:5
└─(neg)─ "per_terminal.moving_sum_frauds">=0.5 [s:6.94014e-07 n:1300740 np:84741 miss:0] ; pred:-0.0408967
├─(pos)─ "per_terminal.moving_count_transaction_28d">=23.5 [s:5.77336e-06 n:84741 np:68762 miss:1] ; pred:-0.00260123
| ├─(pos)─ "per_terminal.moving_count_transaction_28d">=31.5 [s:7.97811e-07 n:68762 np:35992 miss:0] ; pred:-0.0166571
| | ├─(pos)─ pred:-0.0269997
| | └─(neg)─ pred:-0.00529765
| └─(neg)─ "per_terminal.moving_count_transaction_7d">=13.5 [s:2.81166e-05 n:15979 np:8 miss:0] ; pred:0.0578851
| ├─(pos)─ pred:2.93294
| └─(neg)─ pred:0.0564449
└─(neg)─ "per_terminal.moving_count_transaction_28d">=10.5 [s:3.48456e-07 n:1215999 np:1124099 miss:1] ; pred:-0.0435654
├─(pos)─ "per_terminal.moving_count_transaction_28d">=20.5 [s:3.55088e-08 n:1124099 np:910721 miss:1] ; pred:-0.0415172
| ├─(pos)─ pred:-0.0404104
| └─(neg)─ pred:-0.0462414
└─(neg)─ "per_terminal.moving_count_transaction_28d">=3.5 [s:6.14969e-07 n:91900 np:64839 miss:1] ; pred:-0.0686185
├─(pos)─ pred:-0.0624707
└─(neg)─ pred:-0.083349
例如，如果客户的卡被盗，我们可以查看 PDP 模型，了解过去 4 周内的欺诈次数与交易为欺诈的可能性之间的关系。
输入 [69]
已复制！
model.analyze(test_ds_pd, sampling=0.1)
model.analyze(test_ds_pd, sampling=0.1)
输出 [69]
变量重要性衡量输入特征对模型的重要性。
1. "per_terminal.moving_sum_frauds" 0.005308 ################
2. "per_terminal.moving_count_transaction_28d" 0.001118 ###
3. "per_terminal.moving_count_transaction_7d" 0.000358 #
4. "calendar_hour" 0.000000
5. "per_terminal.moving_count_transaction_1d" -0.000007
6. "calendar_day_of_week" -0.000007
1. "per_terminal.moving_sum_frauds" 0.207669 ################
2. "per_terminal.moving_count_transaction_28d" 0.058980 ####
3. "per_terminal.moving_count_transaction_7d" 0.023943 #
4. "calendar_hour" 0.000144
5. "calendar_day_of_week" -0.000243
6. "per_terminal.moving_count_transaction_1d" -0.001815
1. "per_terminal.moving_sum_frauds" 0.231211 ################
2. "per_terminal.moving_count_transaction_28d" 0.015302 #
3. "calendar_hour" 0.001647
4. "per_terminal.moving_count_transaction_7d" 0.001499
5. "per_terminal.moving_count_transaction_1d" 0.000363
6. "calendar_day_of_week" -0.000701
1. "per_terminal.moving_sum_frauds" 0.207691 ################
2. "per_terminal.moving_count_transaction_28d" 0.059061 ####
3. "per_terminal.moving_count_transaction_7d" 0.023948 #
4. "calendar_hour" 0.000115
5. "calendar_day_of_week" -0.000204
6. "per_terminal.moving_count_transaction_1d" -0.001902
1. "per_terminal.moving_sum_frauds" 0.900000 ################
2. "per_terminal.moving_count_transaction_28d" 0.290564 ##
3. "per_terminal.moving_count_transaction_7d" 0.215782
4. "calendar_hour" 0.190089
5. "calendar_day_of_week" 0.188707
6. "per_terminal.moving_count_transaction_1d" 0.180135
1. "per_terminal.moving_sum_frauds" 88.000000 ################
2. "per_terminal.moving_count_transaction_28d" 8.000000 #
3. "per_terminal.moving_count_transaction_7d" 2.000000
4. "calendar_day_of_week" 1.000000
1. "per_terminal.moving_count_transaction_28d" 859.000000 ################
2. "per_terminal.moving_sum_frauds" 824.000000 ###############
3. "per_terminal.moving_count_transaction_7d" 525.000000 ########
4. "calendar_hour" 306.000000 ###
5. "calendar_day_of_week" 214.000000 #
6. "per_terminal.moving_count_transaction_1d" 132.000000
1. "per_terminal.moving_sum_frauds" 2574.658942 ################
2. "per_terminal.moving_count_transaction_28d" 692.886033 ####
3. "per_terminal.moving_count_transaction_7d" 305.556677 #
4. "calendar_hour" 83.875978
5. "calendar_day_of_week" 79.349436
6. "per_terminal.moving_count_transaction_1d" 34.315195