ium_434742/avocado-preprocessing.py

import sys
import kaggle
import pandas as pd
import numpy as np
from sklearn import preprocessing
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error


device = 'cpu'

# kaggle
kaggle.api.authenticate()
kaggle.api.dataset_download_files('timmate/avocado-prices-2020', path='.', unzip=True)

# wczytanie danych
avocado_with_year = pd.read_csv('avocado-updated-2020.csv')

# usuniecie redundantnej kolumny 'year' i zamiana wartosci 'type' na 0 lub 1
new = ['date', 'average_price', 'total_volume', '4046', '4225', '4770', 'total_bags', 'small_bags', 'large_bags', 'xlarge_bags', 'type', 'geography']
avocado = avocado_with_year[new]
avocado.to_csv("avocado.csv", index=False)
avocado = pd.read_csv('avocado.csv')
avocado['type'] = avocado.type.map(dict(organic=1, conventional=0))

# usuniecie wierszy z pustymi wartosciami
avocado.isnull().sum()
avocado.dropna()

# preprocessing
num_values = avocado.select_dtypes(include='float64').values
scaler = preprocessing.MinMaxScaler()
x_scaled = scaler.fit_transform(num_values)
num_columns = avocado.select_dtypes(include='float64').columns
avocado_normalized = pd.DataFrame(x_scaled, columns=num_columns)
for col in avocado.columns:
    if col in num_columns: 
        avocado[col] = avocado_normalized[col]
        
avocado_normalized['type'] = avocado['type']
avocado_normalized['geography'] = avocado['geography']

# parametr CUTOFF
cutoff_param = int(sys.argv[1])
avocado_normalized = avocado_normalized.head(cutoff_param)


# podział na train/dev/test
avocado_train, avocado_validate, avocado_test = np.split(avocado_normalized.sample(frac=1), [int(.6*len(avocado_normalized)), int(.8*len(avocado_normalized))])

print("Avocado: ".ljust(20), np.size(avocado_normalized))
print("Avocado (train) : ".ljust(20), np.size(avocado_train))
print("Avocado (validate): ".ljust(20), np.size(avocado_validate))
print("Avocado (test) ".ljust(20), np.size(avocado_test))

# sprawdzenie danych
avocado_normalized.describe(include = 'all')
avocado_train.describe(include= 'all')
avocado_validate.describe(include = 'all')
avocado_test.describe(include = 'all')

avocado_normalized.geography.value_counts() 
avocado_test.geography.value_counts() 
avocado_train.geography.value_counts() 

pd.value_counts(avocado_normalized['type']).plot.bar()
pd.value_counts(avocado_train['type']).plot.bar()
pd.value_counts(avocado_test['type']).plot.bar()

avocado_normalized['average_price'].hist()
avocado_train['average_price'].hist()
avocado_validate['average_price'].hist()
avocado_test['average_price'].hist()

# zapis do plików
avocado_train.to_csv('avocado_train.csv')
avocado_validate.to_csv('avocado_validate.csv')
avocado_test.to_csv('avocado_test.csv')


# print(avocado_train[:10])
# print(avocado_test[:10])
#print(avocado_normalized)