Week 11

Violy Lislianty Puisetya 00000036447

import numpy as np import matplotlib.pyplot as plt import cv2 from sklearn.cluster import DBSCAN

def cluster_gen(n_clusters, pts_minmax=(10, 100), x_mult=(1, 4), y_mult=(1, 3), x_off=(0, 50), y_off=(0, 50)): # n_clusters = number of clusters to generate # pts_minmax = range of number of points per cluster # x_mult = range of multiplier to modify the size of cluster in the x-direction # y_mult = range of multiplier to modify the size of cluster in the y-direction # x_off = range of cluster position offset in the x-direction # y_off = range of cluster position offset in the y-direction # Initialize some empty lists to receive cluster member positions clusters_x = [] clusters_y = [] # Generate random values given parameter ranges n_points = np.random.randint(pts_minmax[0], pts_minmax[1], n_clusters) x_multipliers = np.random.randint(x_mult[0], x_mult[1], n_clusters) y_multipliers = np.random.randint(y_mult[0], y_mult[1], n_clusters) x_offsets = np.random.randint(x_off[0], x_off[1], n_clusters) y_offsets = np.random.randint(y_off[0], y_off[1], n_clusters) # Generate random clusters given parameter values for idx, npts in enumerate(n_points): xpts = np.random.randn(npts) * x_multipliers[idx] + x_offsets[idx] ypts = np.random.randn(npts) * y_multipliers[idx] + y_offsets[idx] clusters_x.append(xpts) clusters_y.append(ypts) # Return cluster positions return clusters_x, clusters_y

n_clusters = 50 clusters_x, clusters_y = cluster_gen(n_clusters)

data = np.float32((np.concatenate(clusters_x), np.concatenate(clusters_y))).transpose()

max_distance = 1 db = DBSCAN(eps=max_distance, min_samples=10).fit(data)

core_samples_mask = np.zeros_like(db.labels_, dtype=bool) core_samples_mask[db.core_sample_indices_] = True

labels = db.labels_ n_clusters = len(set(labels)) - (1 if -1 in labels else 0) unique_labels = set(labels)

min_x = np.min(data[:, 0]) max_x = np.max(data[:, 0]) min_y = np.min(data[:, 1]) max_y = np.max(data[:, 1]) fig = plt.figure(figsize=(12,6)) plt.subplot(121) plt.plot(data[:, 0], data[:, 1], 'ko') plt.xlim(min_x, max_x) plt.ylim(min_y, max_y) plt.title('Original Data', fontsize = 20) plt.subplot(122)

colors = [plt.cm.Spectral(each) for each in np.linspace(0, 1, len(unique_labels))] for k, col in zip(unique_labels, colors): if k == -1: # Black used for noise. col = [0, 0, 0, 1] class_member_mask = (labels == k) xy = data[class_member_mask & core_samples_mask] plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col), markeredgecolor='k', markersize=7) xy = data[class_member_mask & core_samples_mask] plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col), markeredgecolor='k', markersize=3) plt.xlim(min_x, max_x) plt.ylim(min_y, max_y) plt.title('DBSCAN: %d clusters found' % n_clusters, fontsize = 20) fig.tight_layout() plt.subplots_adjust(left=0.03, right=0.98, top=0.9, bottom=0.05)

import numpy as np import pandas as pd import os #print(os.listdir("../input")) import matplotlib.pyplot as plt import seaborn as sns import warnings warnings.filterwarnings('ignore') %matplotlib inline

df = pd.read_csv('german_credit_data.csv') df.head()

df.isnull().sum()

df.dtypes

fig, axes = plt.subplots(1, 2, figsize=(12, 8)) sns.boxplot(x="Sex", y="Duration", data=df, orient='v', ax=axes[0]) sns.boxplot(x="Sex", y="Credit amount", data=df, orient='v', ax=axes[1])

df_group_one = df[['Sex', 'Credit amount', 'Duration']] df_group_one.groupby(['Sex'], as_index=False).mean()

df_female = df[df['Sex'] == "female"] print(df_female.shape) df_female.head()

Percentage = (df_female.shape[0]/df.shape[0])*100 print('Female Percentage: ', round(Percentage), '%')

from sklearn.cluster import DBSCAN import sklearn.utils from sklearn.preprocessing import StandardScaler Clus_dataSet = df_female[['Age', 'Credit amount', 'Duration']] Clus_dataSet = np.nan_to_num(Clus_dataSet) Clus_dataSet = np.array(Clus_dataSet, dtype=np.float64) Clus_dataSet = StandardScaler().fit_transform(Clus_dataSet) # Compute DBSCAN db = DBSCAN(eps=0.5, min_samples=4).fit(Clus_dataSet) core_samples_mask = np.zeros_like(db.labels_, dtype=bool) core_samples_mask[db.core_sample_indices_] = True labels = db.labels_ df_female['Clus_Db'] = labels realClusterNum = len(set(labels)) - (1 if -1 in labels else 0) clusterNum = len(set(labels)) # A sample of clusters print(df_female[['Age', 'Credit amount', 'Duration', 'Clus_Db']].head()) # Number of labels print('number of labels: ', set(labels))

# Black removed and is used for noise instead. unique_labels = set(labels) colors = [plt.cm.Spectral(each) for each in np.linspace(0, 1, len(unique_labels))] for k, col in zip(unique_labels, colors): if k == -1: # Black used for noise. col = [0, 0, 0, 1] class_member_mask = (labels == k) xy = Clus_dataSet[class_member_mask & core_samples_mask] plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col), markeredgecolor='k', markersize=14) xy = Clus_dataSet[class_member_mask & ~core_samples_mask] plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col), markeredgecolor='k', markersize=6) plt.title('Estimated number of clusters: %d' % realClusterNum) plt.show() n_noise_ = list(labels).count(-1) print('number of noise(s): ', n_noise_)

for clust_number in set(labels): clust_set = df_female[df_female.Clus_Db == clust_number] if clust_number != -1: print('Cluster '+str(clust_number)+', Avg Age: '+ str(round(np.mean(clust_set.Age)))+\ ', Avg Credit amount: '+ str(round(np.mean(clust_set['Credit amount'])))+\ ', Avg Duration: '+ str(round(np.mean(clust_set['Duration'])))+\ ', Count: '+ str(np.count_nonzero(clust_set.index)))

pip install mlxtend

dataset = [['Milk', 'Onion', 'Nutmeg', 'Kidney Beans', 'Eggs', 'Yogurt'], ['Dill', 'Onion', 'Nutmeg', 'Kidney Beans', 'Eggs', 'Yogurt'], ['Milk', 'Apple', 'Kidney Beans', 'Eggs'], ['Milk', 'Unicorn', 'Corn', 'Kidney Beans', 'Yogurt'], ['Corn', 'Onion', 'Onion', 'Kidney Beans', 'Ice Cream', 'Eggs']]

import pandas as pd from mlxtend.preprocessing import TransactionEncoder te = TransactionEncoder() te_ary = te.fit(dataset).transform(dataset) df = pd.DataFrame(te_ary, columns = te.columns_) df

from mlxtend.frequent_patterns import apriori apriori(df, min_support=0.6)

apriori(df, min_support=0.6, use_colnames=True)

frequent_itemsets = apriori(df, min_support=0.6, use_colnames=True) frequent_itemsets['length'] = frequent_itemsets['itemsets'].apply(lambda x: len(x)) frequent_itemsets

frequent_itemsets[ (frequent_itemsets['length'] == 2) & (frequent_itemsets['support'] >= 0.8) ]

frequent_itemsets[ frequent_itemsets['itemsets'] == {'Onion', 'Eggs'} ]

from mlxtend.frequent_patterns import fpgrowth fpgrowth(df, min_support=0.6)

fpgrowth(df, min_support=0.6, use_colnames=True)

import pandas as pd from mlxtend.preprocessing import TransactionEncoder te = TransactionEncoder() te_ary = te.fit(dataset).transform(dataset) df = pd.DataFrame(te_ary, columns = te.columns_)

from mlxtend.frequent_patterns import apriori %timeit -n 100 -r 10 apriori(df, min_support=0.6)

from mlxtend.frequent_patterns import fpgrowth %timeit -n 100 -r 10 fpgrowth(df, min_support=0.6)