rdoume

This document summarizes some potentially useful papers and code repositories on Sentiment analysis / document classification

• CNN:

  1. Related Paper: Convolutional Neural Networks for Sentence Classification. EMNLP 2014

     A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification

     Code:

rdoume

# List unique values in a DataFrame column
# h/t @makmanalp for the updated syntax!
df['Column Name'].unique()

# Convert Series datatype to numeric (will error if column has non-numeric values)
# h/t @makmanalp
pd.to_numeric(df['Column Name'])

# Convert Series datatype to numeric, changing non-numeric values to NaN
# h/t @makmanalp for the updated syntax!

rdoume

# List unique values in a DataFrame column
# h/t @makmanalp for the updated syntax!
df['Column Name'].unique()

# Convert Series datatype to numeric (will error if column has non-numeric values)
# h/t @makmanalp
pd.to_numeric(df['Column Name'])

# Convert Series datatype to numeric, changing non-numeric values to NaN
# h/t @makmanalp for the updated syntax!

rdoume

# coding: utf-8
# Author: Axel ARONIO DE ROMBLAY <[email protected]>
# License: BSD 3 clause

import numpy as np
import pandas as pd
import warnings

import os

rdoume

def getTopNewEntities(conn, country, category=None, window=-2, limit=100, count=None):
    numday = window
    now = pendulum.now(tz='Europe/Paris')
    all_en = []
    cur = conn.cursor()
    for i in range(0, abs(numday)):
        from_date = now.subtract(days=abs(numday + i)).to_datetime_string()
        to_date = now.subtract(days=abs(numday + i + 1)).to_datetime_string()
        query = getQueryTopEntity(from_date, to_date, country, category)

rdoume

Awesome Data Science with Python

Core - Ce qu'on va utiliser

pandas
scikit-learn

plotly-express

matplotlib
seaborn

rdoume

Make Docs

You must ensure that there is a folder docs in your main folder. This folder docs must have:

• a Makefile
• a conf.py file
• an index.rst file
• 2 folders : _static and _template

rdoume

SPONSORED_HASHTAGS = ["#ad", "#brandambassador", "#collaboration", "#disclosure", "#gift", "#gifted", "#giftedby",
                      "#giftfrom", "#partner", "#promo", "#promotion", "#sp", "#spon", "#sponsored", "#sponsor",
                      "#sponsorship", "#sponsoreret", "#sponsoredpost", ""]

SPONSORED_PHRASES = ["brought to you by", "compensated by", "gift from", "gifted by", "in collaboration with",
                     "collaborated with", "in partnership with", "paid ad", "paid advertisement", "paid by",
                     "paid for by", "paid partnership with", "paid post", "paid promo", "paid promotion",
                     "paid sponsorship", "partnered up with", "partnered with", "partnering with", "partnership with",
                     "sponsored by", "sponsored post", "teamed up with", "teamed with", "teaming up with",
                     "teaming with", "brand partner", "working with", "promo code", "coupon code", "discount code",

rdoume

#!/bin/bash
#Ubuntu28.04
curl -O http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-repo-ubuntu1804_10.0.130-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu1804_10.0.130-1_amd64.deb
sudo apt-key adv --fetch-keys http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/7fa2af80.pub
sudo apt-get update
sudo apt-get install cuda
conda install pytorch torchvision cudatoolkit=10.1 -c pytorch

rdoume

#!/bin/bash
#Ubuntu28.04
curl -O http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-repo-ubuntu1804_10.0.130-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu1804_10.0.130-1_amd64.deb
sudo apt-key adv --fetch-keys http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/7fa2af80.pub
sudo apt-get update
sudo apt-get install cuda
conda install pytorch torchvision cudatoolkit=10.1 -c pytorch