audhiaprilliant

# Calculate the f-score
fscore = (2 * precision * recall) / (precision + recall)

# Find the optimal threshold
index = np.argmax(fscore)
thresholdOpt = round(thresholds[index], ndigits = 4)
fscoreOpt = round(fscore[index], ndigits = 4)
recallOpt = round(recall[index], ndigits = 4)
precisionOpt = round(precision[index], ndigits = 4)
print('Best Threshold: {} with F-Score: {}'.format(thresholdOpt, fscoreOpt))

audhiaprilliant

# Array for finding the optimal threshold
thresholds = np.arange(0.0, 1.0, 0.0001)
fscore = np.zeros(shape=(len(thresholds)))
print('Length of sequence: {}'.format(len(thresholds)))

# Fit the model
for index, elem in enumerate(thresholds):
    # Corrected probabilities
    y_pred_prob = (y_pred > elem).astype('int')
    # Calculate the f-score

audhiaprilliant

audhiaprilliant

# Import module for data manipulation
import pandas as pd
# Import module for linear algebra
import numpy as np
# Import module for Fuzzy string matching
from fuzzywuzzy import fuzz, process
# Import module for regex
import re
# Import module for iteration
import itertools

audhiaprilliant

# Import module for data manipulation
import pandas as pd
# Import module for linear algebra
import numpy as np
# Import module for Fuzzy string matching
from fuzzywuzzy import fuzz, process
# Import module for binary search

def stringMatching(
    df: pd.DataFrame,

audhiaprilliant

# Install pakcage for cluster ensemble
install.packages('diceR')
install.packages('treemapify')
library(diceR)
library(dplyr)
library(ggplot2)
library(treemapify)

# Load the order data
df_orders = read.csv(file = '../data/olist_orders_dataset.csv', header = TRUE, sep = ',')

audhiaprilliant

# Group customer by their customer segment
rfm_level_agg = rfm %>%
  group_by(`Customer Segment`) %>%
  summarize(
    Recency = mean(Recency),
    Frequency = mean(Frequency),
    `Monetary Mean` = mean(Monetary),
    `Monetary Count` = n(),
    `Marketing Action` = unique(`Marketing Action`)
  )

audhiaprilliant

audhiaprilliant

audhiaprilliant

# ---------- Central Limit Theorem ----------
# Parameters
sample_mean = 100000
sample_size = 20
set.seed(1234)

# 1 Exponential Distribution
x = rexp(n = 4000, rate = 0.1)
hist(x)
mean(x)