from pyspark.sql.functions import col
import altair as alt

import pandas as pd
from matplotlib import pyplot as plt
get_ipython().run_line_magic('matplotlib', 'inline')
csv = spark.read.option("header",True).csv("hdfs://localhost:9000/data2/porn_data_movie_tags.csv")
tag_csv = spark.read.option("header",True).csv("hdfs://localhost:9000/data2/porn_data_tag.csv")
csv.show()

+---+--------+------+
| id|movie_id|tag_id|
+---+--------+------+
|  1|    9909|     1|
|  2|    9909|     2|
|  3|    9909|     3|
|  4|    9909|     4|
|  5|    9910|     5|
|  6|    9910|     6|
|  7|    9910|     7|
|  8|    9910|     8|
|  9|    9910|     9|
| 10|    9910|    10|
| 11|    9911|    12|
| 12|    9911|     2|
| 13|    9911|     1|
| 14|    9911|    13|
| 15|    9910|    11|
| 16|    9911|    14|
| 17|    9911|    15|
| 18|    9911|     5|
| 19|    9910|    16|
| 20|    9910|    17|
+---+--------+------+
only showing top 20 rows