Learn practical skills, build real-world projects, and advance your career
Updated 5 years ago
import pandas as pd
import numpy as nppd.set_option('display.max_colwidth', -1)df = pd.read_csv("myntra_train_dataset.csv")rdf = pd.read_csv("all_2_tta.csv")cond1 = df["Link_to_the_image"].str.contains("Self")
cond2 = df.Link_to_the_image.notnull()
total = df[cond1 & cond2]["Sub_category"].count()
print(total)
(df[cond1 & cond2]["Sub_category"].value_counts()/total)*100
523
Solid 31.357553
Self Design 17.208413
Geometric 12.619503
Typography 10.707457
Striped 9.177820
Abstract 7.839388
Conversational 2.676864
Checked 1.720841
Floral 1.529637
Graphic 1.338432
Colourblocked 1.338432
Sports and Team Jersey 0.956023
People and Places 0.573614
Polka Dots 0.191205
Humour and Comic 0.191205
Varsity 0.191205
Camouflage 0.191205
Sports 0.191205
Name: Sub_category, dtype: float64