def predict_ffm():
"""
Function to run prediction process:
- Get all posts in a model
- Get only new posts
- Generate pairs with similar posts for each user
- Load a model from disk
- Get FFM predictions
- Save recommendations to a mongo database
"""
database_url = config['database_url']
database = config['database_name']
utils.log("FFM predict", "Prepare model...")
model = ffm.read_model(config['model_path'] + "model.bin")
mappings = joblib.load(config['model_path'] + "mappings.pkl")
while True:
utils.log("FFM predict", "Get posts...")
posts = get_posts(database_url, database)
utils.log("FFM predict", "Create dataset...")
events = utils.get_events(database_url, database)
dataset = create_dataset(posts, events)
utils.log("FFM predict", "Extend events...")
dataset = extend_events(dataset, posts)
mappings, ffm_dataset_X, ffm_dataset_y = create_ffm_dataset(
dataset, mappings)
ffm_dataset = ffm.FFMData(ffm_dataset_X, ffm_dataset_y)
dataset["prediction"] = model.predict(ffm_dataset)
utils.log("FFM predict", "Save recommendations...")
save_recommendations(
dataset[["user_id", "post_permlink", "prediction"]], database_url,
database)
def get_posts(url, database):
events = utils.get_events(url, database)
posts = utils.get_posts(url, database, events,
{'similar_posts': {
'$exists': True
}})
return utils.preprocess_posts(posts)
def get_posts(url, database):
events = utils.get_events(url, database)
posts = utils.get_posts(url, database, events,
{'inferred_vector': {
'$exists': False
}})
return utils.preprocess_posts(posts)
def get_posts(url, database):
events = utils.get_events(url, database)
posts = utils.get_posts(url, database, events,
{'inferred_vector': {
'$exists': True
}})
return utils.preprocess_posts(posts, include_all_tags=True)
def train_ffm():
"""
Function to train FFM model
- Get all events from mongo database
- Convert them to a set of unique user-post pairs with a coefficient depending on user sympathy
- Extend events with a posts info
- Convert events to a format for FFM algorithm
- Build model with chosen train and test set
- Save trained model
"""
database_url = config['database_url']
database = config['database_name']
utils.log("FFM train", "Prepare events...")
events = utils.get_events(database_url, database)
events.to_csv(config['model_path'] + "prepared_events.csv")
# events = pd.read_csv("prepared_events.csv").drop(["Unnamed: 0"], axis=1)
utils.log("FFM train", "Prepare posts...")
posts = get_posts(database_url, database, events)
posts.to_csv(config['model_path'] + "prepared_posts.csv")
# posts = pd.read_csv("prepared_posts.csv").drop(["Unnamed: 0"], axis=1)
utils.log("FFM train", "Extend events...")
events = extend_events(events, posts)
utils.log("FFM train", "Save events...")
events.to_csv(config['model_path'] + "extended_events.csv")
# events = pd.read_csv("extended_events.csv").drop(["Unnamed: 0"], axis=1)
utils.log("FFM train", "Create ffm dataset...")
mappings, X, y = create_ffm_dataset(events)
joblib.dump(X, config['model_path'] + "X.pkl")
joblib.dump(y, config['model_path'] + "y.pkl")
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.3)
utils.log("FFM train", "Build model...")
model, train_auc_roc, test_auc_roc = build_model(train_X, train_y, test_X, test_y)
utils.log("FFM train", train_auc_roc)
utils.log("FFM train", test_auc_roc)
os.system("ffm_predict stop")
model.save_model(config['model_path'] + "model.bin")
joblib.dump(mappings, config['model_path'] + "mappings.pkl")
os.system("ffm_predict start")
from flask import Flask, jsonify, request, render_template
from .config import config as config_flask
import json
from flask_cors import CORS
import sys
from pymongo import MongoClient
import pandas as pd
import pdb
from golosio_recommendation_model.model.utils import get_events
from golosio_recommendation_model.config import config
database_url = config['database_url']
database_name = config['database_name']
events = get_events(database_url, database_name)
app = Flask(__name__)
port = 8080 # Use desired port
@app.route('/users')
def users():
return jsonify(events[events["like"] >= 0.7]["user_id"].unique().tolist())
@app.route('/history')
def history():
user = request.args.get("user")
user_events = events[(events["user_id"] == user) & (events["like"] >= 0.7)]
return jsonify(user_events["post_permlink"].unique().tolist())
def get_posts(url, database):
events = utils.get_events(url, database)
posts = utils.get_posts(url, database, events)
return utils.preprocess_posts(posts)