Calculating the cosine similarity between all the rows of a dataframe in pyspark

Question

I have a dataset containing workers with their demographic information like age gender,address etc and their work locations. I created an RDD from the dataset and converted

Answer 1

About this issue, due to the fact that I'm working in a project with pyspark where I have to use cosine similarity, I have to say that the code of @MaFF is correct, indeed, I hesitated when I see his code, due to the fact he was using the dot product of the vectors' L2 Norm, and the theroy says: Mathematically, it is the ratio of the dot product of the vectors and the product of the magnitude of the two vectors.

And here is my code adapted with the same results, so I came to the conclusion that SKLearn caculates tfidf in a different way, so if you try to replay this excersice using sklearn, you will get a different result.

d = [{'id': '1', 'office': 'Delhi, Mumbai, Gandhinagar'}, {'id': '2', 'office': 'Delhi, Mandi'}, {'id': '3', 'office': 'Hyderbad, Jaipur'}]
df_fussion = spark.createDataFrame(d)
df_fussion = df_fussion.withColumn('office', F.split('office', ', '))


from pyspark.ml.feature import HashingTF, IDF
hashingTF = HashingTF(inputCol="office", outputCol="tf")
tf = hashingTF.transform(df_fussion)

idf = IDF(inputCol="tf", outputCol="feature").fit(tf)
data = idf.transform(tf)   

@udf
def sim_cos(v1,v2):
    try:
        p = 2
        return float(v1.dot(v2))/float(v1.norm(p)*v2.norm(p))
    except:
        return 0

result = data.alias("i").join(data.alias("j"), F.col("i.ID") < F.col("j.ID"))\
    .select(
        F.col("i.ID").alias("i"),
        F.col("j.ID").alias("j"),
        sim_cos("i.feature", "j.feature").alias("sim_cosine"))\
    .sort("i", "j")
result.show()

I also want to share with you some simply test that I did with simply vectors where the results are corrects:

Kind regards,