victorkohler

def get_negatives(uids, iids, items, df_test):
    """Returns a pandas dataframe of 100 negative interactions
    based for each user in df_test.

    Args:
        uids (np.array): Numpy array of all user ids.
        iids (np.array): Numpy array of all item ids.
        items (list): List of all unique items.
        df_test (dataframe): Our test set.

victorkohler

def get_train_instances():
     """Samples a number of negative user-item interactions for each
     user-item pair in our testing data.

     Returns:
         user_input (list): A list of all users for each item
         item_input (list): A list of all items for every user,
             both positive and negative interactions.
         labels (list): A list of all labels. 0 or 1.
     """

victorkohler

for epoch in range(epochs):

    # Get our training input.
    user_input, item_input, labels = get_train_instances()

    # Generate a list of minibatches.
    minibatches = random_mini_batches(user_input, item_input, labels)

    # This has noting to do with tensorflow but gives

victorkohler

import tensorflow as tf
import numpy as np
import pandas as pd
import math
import heapq
from tqdm import tqdm

# Load and prepare our data.
uids, iids, df_train, df_test, df_neg, users, items, item_lookup = load_dataset()

victorkohler

#-------------
# HYPERPARAMS
#-------------

num_neg = 4
latent_features = 8
epochs = 20
batch_size = 256
learning_rate = 0.001

victorkohler

#-------------
# HYPERPARAMS
#-------------

num_neg = 6
latent_features = 8
epochs = 20
batch_size = 256
learning_rate = 0.001

victorkohler

import pandas as pd
import numpy as np

from sklearn.metrics.pairwise import cosine_similarity
from scipy import sparse

#------------------
# LOAD THE DATASET
#------------------

victorkohler

#------------------------
# ITEM-ITEM CALCULATIONS
#------------------------

# As a first step we normalize the user vectors to unit vectors.

# magnitude = sqrt(x2 + y2 + z2 + ...)
magnitude = np.sqrt(np.square(data_items).sum(axis=1))

victorkohler

import random
import pandas as pd
import numpy as np

import scipy.sparse as sparse
from scipy.sparse.linalg import spsolve
from sklearn.preprocessing import MinMaxScaler

#-------------------------
# LOAD AND PREP THE DATA