Load CSV Data in Metaflow steps

load_csv_data.py

from metaflow import FlowSpec, step
url = "https://raw.githubusercontent.com/Netflix/metaflow/master/metaflow/tutorials/02-statistics/movies.csv"
local_path = "./movies.csv"
class CSVFlow(FlowSpec):
    
    @step
    def start(self):
        self.next(self.get_csv_from_web)
        
    @step
    def get_csv_from_web(self):
        import pandas as pd
        self.df = pd.read_csv(url)
        self.df.to_csv(local_path)
        self.next(self.read_csv_locally)
        
    @step
    def read_csv_locally(self):
        import csv
        with open(local_path, newline='') as csvfile:
            reader = csv.reader(csvfile, delimiter=' ', quotechar='|')
            row = next(reader)
            print(f"First Movie in the list is {next(reader)[0].split(',')[1]}.")
        self.next(self.end)
        
    @step
    def end(self):
        print("Top Five Highest Grossing Movies:")
        print(self.df.sort_values(by='gross')[-5:][::-1])
        
if __name__ == "__main__":
    CSVFlow()

This Code Answers the Question:

*I have a CSV (locally or on the web) and want to access it in a Metaflow flow. How can I read this data in and write it to disk?

For more information, visit: https://docs-git-poc-rhs-panel-metaflow.vercel.app/how-to-guides/csv