Created
August 27, 2019 20:49
-
-
Save sharmanirek/172c9408e8393462ae54dfae83764413 to your computer and use it in GitHub Desktop.
Pyspark MLLib || GMM clustering Error
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# coding: utf-8 | |
# In[1]: | |
import pyspark | |
import sys | |
print("python version = {}".format(sys.version)) | |
print("pyspark version = {}".format(pyspark.__version__)) | |
# In[2]: | |
from pyspark.sql.types import DoubleType, StringType, IntegerType, ArrayType | |
from pyspark.ml.clustering import GaussianMixture | |
from pyspark.sql import SQLContext | |
from pyspark.sql.session import SparkSession | |
from pyspark.mllib.linalg import Vectors, VectorUDT, DenseVector | |
from pyspark.sql.functions import udf | |
sc = SparkSession.builder.appName('GMM_Demo').master("local[*]").getOrCreate() | |
sql = SQLContext(sc) | |
df = sc.read.csv("GMM_demo_data.csv", header = True) | |
# In[3]: | |
# new_schema = ArrayType(DoubleType(), containsNull=False) | |
new_schema = ArrayType(DoubleType(), containsNull=False) | |
string_parse = udf(lambda x: [float(elem.replace('[','') | |
.replace(']','') | |
.strip()) for elem in x.split(",")], new_schema) | |
df = df.withColumn('features', string_parse('pcaFeatures')) | |
# In[45]: | |
model = GaussianMixture(k=7, seed = 1234, featuresCol = 'features', | |
predictionCol='predictionCol', probabilityCol = 'probabilityCol') | |
output = model.fit(df).transform(df) | |
# In[50]: | |
output.select('probabilityCol').toPandas() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment