jeanmidevacc

from pyspark.ml.recommendations import ALS

# Context , there is dfs_actions is spark dataframe that looks like the pandas dataframe for surprise example https://gist.github.com/jeanmidevacc/a00c9cf8fe9379cd8a818b1d842dbaa1

# Setup the model parameters
als = ALS(
  seed=12,
  userCol="user_id",
  itemCol="item_id",
  ratingCol="rating",

jeanmidevacc

import surprise

# there is pandas dataframe that contains the different ratings between user and item , indexed

# Build a reader
reader = surprise.Reader(rating_scale=(dfp_actions["rating"].min(),dfp_actions["rating"].max()))

#_id column are index id of the user and item
surprise_data = surprise.Dataset.load_from_df(dfp_actions[["user_id", "item_id", "rating"]], reader = reader)
train_set = surprise_train.build_full_trainset()

jeanmidevacc

from pyspark.sql import SparkSession, SQLContext
import pyspark.sql.functions as F
import pyspark.sql.types as T
from pyspark.sql import Window

def build_recommendations(broadcast_dfp_items_factors):
    def build_recommendations_(user_factors, inventory_itemid_encoded, k=5):
        
        # Fetch on the factors for the item that can be recommended , add your rules
        dfp_items_factors_to_rank = broadcast_dfp_items_factors.value[~broadcast_array_items_factors.value["id"].isin(inventory_itemid_encoded)]

jeanmidevacc

from pyspark.sql import SparkSession, SQLContext
import pyspark.sql.functions as F
import pyspark.sql.types as T
from pyspark.sql import Window

dfs_items = #pyspark dataframe that contains items to be indexed (define by itemid)

previous_max_itemid_indexed = 0 #in case it's an incremental process , set a tempora

windowspec = Window.orderBy(F.col("itemid"))# build a window function

jeanmidevacc

if time.time() - last_checked > 2:
        step += 1
        
        # Update the last checked time
        last_checked = time.time()
        particle_states = get_particles_state(handler.data["particles"])
        score = handler.data["score"]

        # Set the next particle's x position before releasing
        observation = {

jeanmidevacc

#!/bin/bash

# Check if the user provided an argument
if [ -z "$1" ]; then
  echo "Please specify the number of runs as an argument."
  exit 1
fi

# Total number of runs specified by the first argument
TOTAL_RUNS=$1

jeanmidevacc

from datetime import datetime
import random

import pandas as pd


class RandomAgent():
    def __init__(self):
        self.creation_date = datetime.utcnow()
        self.tag = "random"    

jeanmidevacc

from pydub import AudioSegment, silence
import pandas as pd

def build_segments(audio, length_segment=10, dbfs=0):
    silences = silence.detect_silence(audio, min_silence_len=1000, silence_thresh=dbfs-16)
    dfp_silences = pd.DataFrame(silences, columns = ["start_timecode", "end_timecode"])

    threshold_segment = int(length_segment * 60 * 1000)
    first_timecode = 0
    last_timecode = int(audio.duration_seconds * 1000)

jeanmidevacc

from pathlib import Path
from openai import OpenAI

client_openai = OpenAI(
    # This is the default and can be omitted
    api_key="sk-XXX",
)

def get_transcript_openai_api(file, language="fr"):
    # f = open(file, "rb")

jeanmidevacc

import torch
from transformers import pipeline

device = "cuda:0" if torch.cuda.is_available() else "cpu"
mapping = {"whisper-tiny" : "tiny", "whisper-small" : "small", "whisper-medium" : "medium", "whisper-base" : "base"}

hf_model_name = "whisper-medium"
size_model = mapping[hf_model_name] #tiny, base, small, medium

model = pipeline(