使用 Amazon Keyspaces 作为数据源训练机器学习模型

# Install missing packages and import dependencies
# Installing Cassandra SigV4
%pip install cassandra-sigv4 # Get Security certificate
!curl https://certs.secureserver.net/repository/sf-class2-root.crt -O # Import
from sagemaker import get_execution_role
from cassandra.cluster import Cluster
from ssl import SSLContext, PROTOCOL_TLSv1_2, CERT_REQUIRED
from cassandra_sigv4.auth import SigV4AuthProvider
import boto3 import pandas as pd
from pandas import DataFrame import csv
from cassandra import ConsistencyLevel
from datetime import datetime
import time
from datetime import timedelta import pandas as pd
import datetime as dt
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.preprocessing import MinMaxScaler # Getting credentials from the role
client = boto3.client("sts") # Get notebook Role
role = get_execution_role()
role_info = {"RoleArn": role, "RoleSessionName": "session1"}
print(role_info) credentials = client.assume_role(**role_info)

# Connect to Cassandra Database from SageMaker Notebook # using temporary credentials from the Role.
session = boto3.session.Session() ###
### You can also pass specific credentials to the session
###
#session = boto3.session.Session(
# aws_access_key_id=credentials["Credentials"]["AccessKeyId"],
# aws_secret_access_key=credentials["Credentials"]["SecretAccessKey"],
# aws_session_token=credentials["Credentials"]["SessionToken"],
#) region_name = session.region_name # Set Context
ssl_context = SSLContext(PROTOCOL_TLSv1_2)
ssl_context.load_verify_locations("sf-class2-root.crt")
ssl_context.verify_mode = CERT_REQUIRED auth_provider = SigV4AuthProvider(session)
keyspaces_host = "cassandra." + region_name + ".amazonaws.com" cluster = Cluster([keyspaces_host], ssl_context=ssl_context, auth_provider=auth_provider, port=9142)
session = cluster.connect() # Read data from Keyspaces system table. # Keyspaces is serverless DB so you don't have to create Keyspaces DB ahead of time.
r = session.execute("select * from system_schema.keyspaces") # Read Keyspaces row into Panda DataFrame
df = DataFrame(r)
print(df)

# Prepare Data
r = session.execute("select * from " + keyspaces_schema + ".online_retail") df = DataFrame(r)
df.head(100) df.count()
df["description"].nunique()
df["totalprice"] = df["quantity"] * df["price"]
df.groupby("invoice").agg({"totalprice": "sum"}).head() df.groupby("description").agg({"price": "max"}).sort_values("price", ascending=False).head()
df.sort_values("price", ascending=False).head()
df["country"].value_counts().head()
df.groupby("country").agg({"totalprice": "sum"}).sort_values("totalprice", ascending=False).head() returned = df[df["invoice"].str.contains("C", na=False)]
returned.sort_values("quantity", ascending=True).head() df.isnull().sum()
df.dropna(inplace=True)
df.isnull().sum()
df.dropna(inplace=True)
df.isnull().sum()
df.describe([0.05, 0.01, 0.25, 0.50, 0.75, 0.80, 0.90, 0.95, 0.99]).T
df.drop(df.loc[df["customer_id"] == ""].index, inplace=True) # Recency Metric
import datetime as dt today_date = dt.date(2011, 12, 9)
df["customer_id"] = df["customer_id"].astype(int) # create get the most recent invoice for each customer
temp_df = df.groupby("customer_id").agg({"invoice_date": "max"})
temp_df["invoice_date"] = temp_df["invoice_date"].astype(str)
temp_df["invoice_date"] = pd.to_datetime(temp_df["invoice_date"]).dt.date
temp_df["Recency"] = (today_date - temp_df["invoice_date"]).dt.days
recency_df = temp_df.drop(columns=["invoice_date"])
recency_df.head() # Frequency Metric
temp_df = df.groupby(["customer_id", "invoice"]).agg({"invoice": "count"})
freq_df = temp_df.groupby("customer_id").agg({"invoice": "count"})
freq_df.rename(columns={"invoice": "Frequency"}, inplace=True) # Monetary Metric
monetary_df = df.groupby("customer_id").agg({"totalprice": "sum"})
monetary_df.rename(columns={"totalprice": "Monetary"}, inplace=True)
rfm = pd.concat([recency_df, freq_df, monetary_df], axis=1) df = rfm
df["RecencyScore"] = pd.qcut(df["Recency"], 5, labels=[5, 4, 3, 2, 1])
df["FrequencyScore"] = pd.qcut(df["Frequency"].rank(method="first"), 5, labels=[1, 2, 3, 4, 5])
df["Monetary"] = df["Monetary"].astype(int)
df["MonetaryScore"] = pd.qcut(df["Monetary"], 5, labels=[1, 2, 3, 4, 5])
df["RFM_SCORE"] = ( df["RecencyScore"].astype(str) + df["FrequencyScore"].astype(str) + df["MonetaryScore"].astype(str)
)
seg_map = { r"[1-2][1-2]": "Hibernating", r"[1-2][3-4]": "At Risk", r"[1-2]5": "Can't Loose", r"3[1-2]": "About to Sleep", r"33": "Need Attention", r"[3-4][4-5]": "Loyal Customers", r"41": "Promising", r"51": "New Customers", r"[4-5][2-3]": "Potential Loyalists", r"5[4-5]": "Champions",
} df["Segment"] = df["RecencyScore"].astype(str) + rfm["FrequencyScore"].astype(str)
df["Segment"] = df["Segment"].replace(seg_map, regex=True)
df.head()
rfm = df.loc[:, "Recency":"Monetary"]
df.groupby("customer_id").agg({"Segment": "sum"}).head()

## Optional Code to save Python DataFrame to S3
from io import StringIO # python3 (or BytesIO for python2) smclient = boto3.Session().client('sagemaker')
sess = sagemaker.Session()
bucket = sess.default_bucket() # Set a default S3 bucket
print(bucket) csv_buffer = StringIO()
df.to_csv(csv_buffer)
s3_resource = boto3.resource('s3')
s3_resource.Object(bucket, ‘out/saved_online_retail.csv').put(Body=csv_buffer.getvalue())

# Training sc = MinMaxScaler((0, 1))
df = sc.fit_transform(rfm) # Clustering
kmeans = KMeans(n_clusters=6).fit(df) # Result
segment = kmeans.labels_ # Visualize the clusters
import matplotlib.pyplot as plt final_df = pd.DataFrame({"customer_id": rfm.index, "Segment": segment})
bucket_data = final_df.groupby("Segment").agg({"customer_id": "count"}).head()
index_data = final_df.groupby("Segment").agg({"Segment": "max"}).head()
index_data["Segment"] = index_data["Segment"].astype(int)
dataFrame = pd.DataFrame(data=bucket_data["customer_id"], index=index_data["Segment"])
dataFrame.rename(columns={"customer_id": "Total Customers"}).plot.bar( rot=70, title="RFM clustering"
)
# dataFrame.plot.bar(rot=70, title="RFM clustering");
plt.show(block=True);

# Create ml_clustering_results table to store results createTable = """CREATE TABLE IF NOT EXISTS %s.ml_clustering_results ( run_id text, segment int, total_customers int, run_date date, PRIMARY KEY (run_id, segment)); """
cr = session.execute(createTable % keyspaces_schema)
time.sleep(20)
print("Table 'ml_clustering_results' created") insert_ml = ( "INSERT INTO " + keyspaces_schema + '.ml_clustering_results' + '("run_id","segment","total_customers","run_date") ' + 'VALUES (?,?,?,?); '
) prepared = session.prepare(insert_ml)
prepared.consistency_level = ConsistencyLevel.LOCAL_QUORUM run_id = "101"
dt = datetime.now() for ind in dataFrame.index: print(ind, dataFrame['customer_id'][ind]) r = session.execute( prepared, ( run_id, ind, dataFrame['customer_id'][ind], dt, ), )

# Delete blog keyspace and tables
deleteKeyspace = "DROP KEYSPACE IF EXISTS blog"
dr = session.execute(deleteKeyspace) time.sleep(5)
print("Dropping %s keyspace. It may take a few seconds to a minute to complete deletion keyspace and table." % keyspaces_schema )