def no_transaction_vs_harmonic():
merchant_data_path = os.path.join(DATASET_DIR,
"MerchantSumAmountPerDay.txt")
data_reader = MerchantData(merchant_data_path)
X = data_reader.get_clean_data()
# Data Selection
harmonic_amount = X[:, 0] # Recency
no_transaction = X[:, 1] # Frequency
# Plotting
title = "Trans vs Harmonic"
labels = ("No Transaction", "Harmonic Sum")
plotlyvisualize.scatter(no_transaction,
harmonic_amount,
title,
labels,
out_path=PLOT_OUT_DIR)
def no_transactions_vs_sum_amounts():
merchant_data_path = os.path.join(DATASET_DIR,
"MerchantSumAmountPerDay.txt")
data_reader = MerchantData(merchant_data_path)
X = data_reader.get_clean_data()
# Data Selection
no_transaction = X[:, 1] # Frequency
sum_amounts = X[:, 2] # Money
# Plotting
title = "No Transactions vs Sum Amounts"
labels = ("No Transaction", "Sum Amounts")
no_transaction = np.log(no_transaction)
#sum_amounts = np.log(sum_amounts)/np.log(1.5)
plotlyvisualize.scatter(no_transaction,
sum_amounts,
title,
labels,
out_path=PLOT_OUT_DIR)
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import norm
from sklearn.neighbors import KernelDensity
import os
from readdata.merchantdata import MerchantData
DATASET_DIR = "dataset"
PLOT_OUT_DIR = "plotsout"
merchant_data_path = os.path.join(DATASET_DIR, "MerchantSumAmountPerDay.txt")
data_reader = MerchantData(merchant_data_path)
X = data_reader.get_clean_data()
# Data Selection
no_transaction = X[:, 1] # Frequency
sum_amounts = X[:, 2] # Money
# Plot a 1D density example
N = 100
np.random.seed(1)
N = no_transaction.shape[0]
X = no_transaction[:,
np.newaxis] #np.random.normal(0, 1, 0.3 * N)[:, np.newaxis]
X_plot = np.linspace(np.min(X), np.max(X), 1000)[:, np.newaxis]
fig, ax = plt.subplots()
for kernel in ['gaussian', 'tophat', 'epanechnikov']:
kde = KernelDensity(kernel=kernel, bandwidth=0.5).fit(X)
log_dens = kde.score_samples(X_plot)