共用方式為

可解譯性 - 表格式 SHAP 說明程式

  • 發行項

在此範例中，我們使用 Kernel SHAP 來說明從成人人口普查資料集組建的表格式分類模型。

首先，我們會匯入套件，並定義稍後會需要的某些 UDF。

import pyspark
from synapse.ml.explainers import *
from pyspark.ml import Pipeline
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.feature import StringIndexer, OneHotEncoder, VectorAssembler
from pyspark.sql.types import *
from pyspark.sql.functions import *
import pandas as pd
from pyspark.sql import SparkSession

# Bootstrap Spark Session
spark = SparkSession.builder.getOrCreate()

from synapse.ml.core.platform import *




vec_access = udf(lambda v, i: float(v[i]), FloatType())
vec2array = udf(lambda vec: vec.toArray().tolist(), ArrayType(FloatType()))

現在，讓我們讀取資料並訓練二元分類模型。

df = spark.read.parquet(
    "wasbs://publicwasb@mmlspark.blob.core.windows.net/AdultCensusIncome.parquet"
)

labelIndexer = StringIndexer(
    inputCol="income", outputCol="label", stringOrderType="alphabetAsc"
).fit(df)
print("Label index assigment: " + str(set(zip(labelIndexer.labels, [0, 1]))))

training = labelIndexer.transform(df).cache()
display(training)
categorical_features = [
    "workclass",
    "education",
    "marital-status",
    "occupation",
    "relationship",
    "race",
    "sex",
    "native-country",
]
categorical_features_idx = [col + "_idx" for col in categorical_features]
categorical_features_enc = [col + "_enc" for col in categorical_features]
numeric_features = [
    "age",
    "education-num",
    "capital-gain",
    "capital-loss",
    "hours-per-week",
]

strIndexer = StringIndexer(
    inputCols=categorical_features, outputCols=categorical_features_idx
)
onehotEnc = OneHotEncoder(
    inputCols=categorical_features_idx, outputCols=categorical_features_enc
)
vectAssem = VectorAssembler(
    inputCols=categorical_features_enc + numeric_features, outputCol="features"
)
lr = LogisticRegression(featuresCol="features", labelCol="label", weightCol="fnlwgt")
pipeline = Pipeline(stages=[strIndexer, onehotEnc, vectAssem, lr])
model = pipeline.fit(training)

訓練模型之後，我們會隨機選取一些要說明的觀察。

explain_instances = (
    model.transform(training).orderBy(rand()).limit(5).repartition(200).cache()
)
display(explain_instances)

我們會建立 TabularSHAP 說明程式、將輸入資料行設定為模型採用的所有功能、指定模型和我們正在嘗試說明的目標輸出資料行。 在此情況下，我們正在嘗試說明「可能性」輸出，這是長度 2 的向量，而我們只查看類別 1 可能性。 如果您要同時說明類別 0 和 1 可能性，則請將 targetClasses 指定為 [0, 1]。 最後，我們從背景資料的訓練資料中取樣 100 個資料列，用於整合 Kernel SHAP 中的功能。

shap = TabularSHAP(
    inputCols=categorical_features + numeric_features,
    outputCol="shapValues",
    numSamples=5000,
    model=model,
    targetCol="probability",
    targetClasses=[1],
    backgroundData=broadcast(training.orderBy(rand()).limit(100).cache()),
)

shap_df = shap.transform(explain_instances)

產生 DataFrame 之後，我們會擷取模型輸出的類別 1 可能性、目標類別的 SHAP 值、原始特徵和 true 標籤。 然後，我們會將其轉換成 Pandas DataFrame，以呈現視覺效果。 對於每個觀察，SHAP 值向量中的第一個元素是基值 (背景資料集的平均輸出)，而下列每個元素都是每個特徵的 SHAP 值。

shaps = (
    shap_df.withColumn("probability", vec_access(col("probability"), lit(1)))
    .withColumn("shapValues", vec2array(col("shapValues").getItem(0)))
    .select(
        ["shapValues", "probability", "label"] + categorical_features + numeric_features
    )
)

shaps_local = shaps.toPandas()
shaps_local.sort_values("probability", ascending=False, inplace=True, ignore_index=True)
pd.set_option("display.max_colwidth", None)
shaps_local

我們使用 plotly subplot 將 SHAP 值視覺化。

from plotly.subplots import make_subplots
import plotly.graph_objects as go
import pandas as pd

features = categorical_features + numeric_features
features_with_base = ["Base"] + features

rows = shaps_local.shape[0]

fig = make_subplots(
    rows=rows,
    cols=1,
    subplot_titles="Probability: "
    + shaps_local["probability"].apply("{:.2%}".format)
    + "; Label: "
    + shaps_local["label"].astype(str),
)

for index, row in shaps_local.iterrows():
    feature_values = [0] + [row[feature] for feature in features]
    shap_values = row["shapValues"]
    list_of_tuples = list(zip(features_with_base, feature_values, shap_values))
    shap_pdf = pd.DataFrame(list_of_tuples, columns=["name", "value", "shap"])
    fig.add_trace(
        go.Bar(
            x=shap_pdf["name"],
            y=shap_pdf["shap"],
            hovertext="value: " + shap_pdf["value"].astype(str),
        ),
        row=index + 1,
        col=1,
    )

fig.update_yaxes(range=[-1, 1], fixedrange=True, zerolinecolor="black")
fig.update_xaxes(type="category", tickangle=45, fixedrange=True)
fig.update_layout(height=400 * rows, title_text="SHAP explanations")
fig.show()

相關內容