import pandas as pd
import numpy as np
def logic(index):
if index % 2 == 0:
return False
return True
df = pd.read_csv('sample_submission.csv', skiprows=(lambda x:logic(x))).sample(n=1000)
df.reset_index(drop=True)
df_column_names = ['pid']
for i in range(1,501):
df_column_names.append('trackuri_' + str(i))
df.columns = df_column_names
df.reset_index(drop=True)
col_names = df_column_names[1:]
for i in col_names:
df[i] = df[i].str[15:]
df
# Input
# A user-created playlist, represented by:
# Playlist metadata (see the dataset README)
# K seed tracks: a list of K tracks in the playlist, where K can equal
# 0, 1, 5, 10, 25, or 100.
# d ={}
# for index, row in df.iterrows():
# for i in row:
# if i is in d.keys():
# d[i].append(1)
# else:
# d.append(i: 1)
small_df = df.sample(n=3)
small_df
# Output
# A list of 500 recommended candidate tracks, ordered by relevance in
# decreasing order.