himangSharatun

The Best of the Best Practices (BOBP) Guide for Python

A "Best of the Best Practices" (BOBP) guide to developing in Python.

In General

Principles

• "Build tools for others that you want to be built for you." - Kenneth Reitz
• "Simplicity is alway better than functionality." - Pieter Hintjens

himangSharatun

from sklearn.feature_extraction.text import CountVectorizer
import json
import pandas
import numpy

corpus_path = 'data/training/training-data.csv'

# prepare training data for bow (corpus)
X_training = []
dataframe = pandas.read_csv(corpus_path, header=None)

himangSharatun

from sklearn.feature_extraction.text import CountVectorizer
import json

vocab_path = 'vocabulary.json'

vocabulary = json.load(open(vocab_path))
vectorizer = CountVectorizer(vocabulary=vocabulary)

def tobow(string):
    return vectorizer.transform([string]).toarray()

himangSharatun

# define baseline model
def baseline_model():
	# create model
	model = Sequential()
	model.add(Dense(5000, input_shape=(len(bow[0]),), activation='relu'))
	model.add(Dropout(0.2))
	model.add(Dense(len(dummy_y[0]), activation='softmax'))
	# Compile model
	model.summary()
	model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

himangSharatun

training_data = "data/training/training-data.csv"
training_label = "data/training/training-label.csv"


X_dataframe = pandas.read_csv(training_data, header=None)
X = X_dataframe.values
Y_dataframe = pandas.read_csv(training_label, header=None)
Y = Y_dataframe.values

dummy_x = []

himangSharatun

import numpy
import pandas
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.wrappers.scikit_learn import KerasClassifier
from keras.utils import np_utils
from sklearn.preprocessing import LabelEncoder
from tobow import tobow

numpy.random.seed(7)

himangSharatun

import pandas
import numpy
from tobow import tobow
from sklearn.preprocessing import LabelEncoder
from keras.models import Sequential, Dense
from keras.models import model_from_json

def evaluate(model_path, weights_path, test_data_path, test_label_path, encoder_path):
    # load test data and label
    X_test = pandas.read_csv(test_data_path, header=None)

himangSharatun

from pandas import read_csv
from pandas import datetime
from matplotlib import pyplot
from statsmodels.tsa.arima_model import ARIMA
from sklearn.metrics import mean_squared_error
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf

file_path = "minyak-goreng-prices.csv"

# Parse the date into pandas.datetime

himangSharatun

from pandas import read_csv
from pandas import datetime
from matplotlib import pyplot
import numpy

file_path = "minyak-goreng-prices.csv"
 
def parser(x):
    splited = x.split('-')
    return datetime.strptime(splited[0] + "-" + splited[1] + "-20" +splited[2], '%d-%b-%Y')

himangSharatun

from pandas import read_csv
from pandas import datetime
from matplotlib import pyplot
import numpy

file_path = "minyak-goreng-prices.csv"
 
def parser(x):
    splited = x.split('-')
    return datetime.strptime(splited[0] + "-" + splited[1] + "-20" +splited[2], '%d-%b-%Y')