tanpengshi

"""
Implementation of algorithm to train random forest classifiers.

Author: Tan Pengshi Alvin
Adapted from: https://towardsdatascience.com/master-machine-learning-random-forest-from-scratch-with-python-3efdd51b6d7a
"""
import numpy as np
import pandas as pd

from scipy import stats

tanpengshi

"""
Implementation of algorithm to train decision tree classifiers.

Author: Tan Pengshi Alvin
Adapted from: https://towardsdatascience.com/decision-tree-from-scratch-in-python-46e99dfea775
"""
import numpy as np
import pandas as pd
import random

tanpengshi

tanpengshi

tanpengshi

tanpengshi

content_matrix = pd.DataFrame(content_matrix,columns=sorted(X_train['product_id'].unique()),index=sorted(X_train['user_id'].unique()))
content_df = content_matrix.stack().reset_index()
content_df = content_df.rename(columns={'level_0':'user_id','level_1':'product_id',0:'predicted_interaction'})
X_valid = X_valid.merge(content_df,on=['user_id','product_id'])

X_valid['predicted_purchase'] = X_valid['predicted_interaction'].apply(lambda x:1 if x>=0.5 else 0)

tanpengshi

product_cat = X_train[['product_id','price_category','category_code','brand']].drop_duplicates('product_id')
product_cat = product_cat.sort_values(by='product_id')

price_cat_matrix = np.reciprocal(euclidean_distances(np.array(product_cat['price_category']).reshape(-1,1))+1)
euclidean_matrix = pd.DataFrame(price_cat_matrix,columns=product_cat['product_id'],index=product_cat['product_id'])

tfidf_vectorizer = TfidfVectorizer()
doc_term = tfidf_vectorizer.fit_transform(list(product_cat['category_code']))
dt_matrix = pd.DataFrame(doc_term.toarray().round(3), index=[i for i in product_cat['product_id']], columns=tfidf_vectorizer.get_feature_names())
cos_similar_matrix = pd.DataFrame(cosine_similarity(dt_matrix.values),columns=product_cat['product_id'],index=product_cat['product_id'])

tanpengshi

X_train_matrix = pd.pivot_table(X_train,values='user_score',index='user_id',columns='product_id')
X_train_matrix = X_train_matrix.fillna(0)

tanpengshi

tanpengshi

group = df.groupby(['user_id','product_id'])['user_score','user_purchase'].sum().reset_index()
group['user_purchase'] = group['user_purchase'].apply(lambda x: 1 if x>1 else x)
group['user_score'] = group['user_score'].apply(lambda x: 100 if x>100 else x)

std = MinMaxScaler(feature_range=(0.025, 1))
std.fit(group['user_score'].values.reshape(-1,1))
group['interaction_score'] = std.transform(group['user_score'].values.reshape(-1,1))

group = group.merge(df[['product_id','category_code','brand','price','price_category']].drop_duplicates('product_id'),on=['product_id'])