Spaces:
Sleeping
Sleeping
File size: 1,374 Bytes
1bedd9b | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | import pandas as pd
import pickle
import os
def obtain_params_opt() :
path = os.path.join(os.path.dirname(__file__), "params", "params_opt.pkl")
with open(path, "rb") as file :
a = pickle.load(file)
path = os.path.join(os.path.dirname(__file__), "params", "columns.pkl")
with open(path, "rb") as file :
columns = pickle.load(file)
return a, columns
def format_data(csv_file, columns) :
df = pd.read_csv(csv_file.name)
df = df.drop(columns=['Unnamed: 0', 'flight'])
df['class'] = df['class'].apply(lambda x: 1 if x=='Business' else 0)
df.stops = pd.factorize(df.stops)[0]
for col in ['airline', 'source_city', 'destination_city', 'departure_time', 'arrival_time']:
counts = df[col].value_counts()
common = counts[counts > 100].index
df[col] = df[col].where(df[col].isin(common), other='Other')
df = pd.get_dummies(df, columns=[
'airline', 'source_city', 'destination_city',
'departure_time', 'arrival_time', 'stops', 'class'
], drop_first=True)
df = df.drop_duplicates()
x = df.copy()
x.insert(0, 'intercept', 1)
for col in columns:
if col not in df.columns:
df[col] = 0
df = df[columns]
X_matrix = df.astype(float).to_numpy()
return X_matrix |