ium_478841/scripts/grab_avocado.py
2022-04-24 13:32:00 +02:00

65 lines
2.5 KiB
Python

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
cols = list(pd.read_csv("data/avocado.csv", nrows=1))
# print("###\n", cols, "\n###")
avocados = pd.read_csv(
"data/avocado.csv").rename(columns={"Unnamed: 0": 'Week'})
avocados.describe(include="all")
# * Retrieve the target column
# y = avocados.AveragePrice
# avocados.drop(['AveragePrice'], axis=1, inplace=True)
# * columns containing numerical values for...
# ['Total Volume', '4046', '4225', '4770', 'Total Bags', 'Small Bags', 'Large Bags', 'XLarge Bags']
# fcols = (avocados.dtypes != 'object')
# float_cols = list(fcols[fcols].index)
# print("Numerical columns: ", float_cols)
# # * ...standarization
# avocados.loc[:, float_cols] = StandardScaler(
# ).fit_transform(avocados.loc[:, float_cols])
# * columns containing objects for...
obj_cols = (avocados.dtypes == 'object')
object_cols = list(obj_cols[obj_cols].index)
print("Object columns: ", object_cols)
# * ...OHE
enc = OneHotEncoder(handle_unknown='ignore', sparse=False)
# encoded_region = enc.fit_transform(
# avocados['region'].to_numpy().reshape(-1, 1)).toarray()
# encoded_region_frame = pd.DataFrame(
# encoded_region, columns=enc.get_feature_names_out())
# encoded_types = enc.fit_transform(
# avocados['type'].to_numpy().reshape(-1, 1)).toarray()
# encoded_types_frame = pd.DataFrame(
# encoded_types, columns=enc.get_feature_names_out())
ohe_df = pd.DataFrame(enc.fit_transform(avocados[object_cols]))
ohe_df.index = avocados.index
avocados = pd.concat([avocados.drop(object_cols, axis=1), ohe_df], axis=1)
all_cols = avocados.columns
print(all_cols)
# avocados = pd.concat([avocados, ohe_df], axis=1)
# * Time for normalization
mM = MinMaxScaler()
avocados_normed = pd.DataFrame(mM.fit_transform(avocados.values), columns=all_cols)
print(avocados_normed.head())
# avocados.loc[:, float_cols] = MinMaxScaler().fit_transform(avocados.loc[:, float_cols])
# print(avocados.head())
avocado_train, avocado_test = train_test_split(
avocados_normed, test_size=2000, random_state=3337)
avocado_train, avocado_valid = train_test_split(
avocado_train, test_size=2249, random_state=3337)
print("Train\n", avocado_train.describe(include="all"), "\n")
print("Valid\n", avocado_valid.describe(include="all"), "\n")
print("Test\n", avocado_test.describe(include="all"))
avocado_train.to_csv("data/avocado.data.train", index=False)
avocado_valid.to_csv("data/avocado.data.valid", index=False)
avocado_test.to_csv("data/avocado.data.test", index=False)