Nov05

# install chromium, its driver, and selenium
!apt install chromium-chromedriver
!cp /usr/lib/chromium-browser/chromedriver /usr/bin
!pip install selenium
# set options to be headless, ..
from selenium import webdriver
options = webdriver.ChromeOptions()
options.add_argument('--headless')
options.add_argument('--no-sandbox')
options.add_argument('--disable-dev-shm-usage')

Nov05

2019-08-01

Check Heroku Logs and Debug

Dash App on Heroku
https://hours-estimate.herokuapp.com/
GitHub Repo
https://github.com/Nov05/DS-Unit-2-Sprint-4-Project

• navigate: Heroku > hours-estimate (or your own app name) > Activity > View build log

Nov05

2019-08-05
Anaconda Logs

Unit 3 Module 1 Python Packages and Environments
https://github.com/Nov05/DS-Unit-3-Sprint-1-Software-Engineering/tree/master/module1-python-modules-packages-and-environments

Managing Environments (Anaconda)
https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html

Windows 10, Anaconda Prompt

Nov05

import pandas as pd
import numpy as np

import matplotlib.pyplot as plt
import seaborn as sns
import pandas_profiling
import plotly
import plotly.graph_objects as go
from sklearn.preprocessing import MinMaxScaler

Nov05

!pip install colorlover
# Successfully installed colorlover-0.3.0

import pandas as pd
import numpy as np

import matplotlib.pyplot as plt

Nov05

Baseline

# baseline score
X_train, X_val, y_train, y_val = train_test_split(
    X_trainval, y_trainval, test_size=0.33, random_state=42)
print("train mean velocity:", y_train.mean())
y_val_pred = [y_train.mean()] * len(y_val)
print('baseline error score:', mean_squared_error(y_val, y_val_pred))

Nov05

'''
Load Yelp JSON files and spit out CSV files
Does not try to reinvent the wheel and uses pandas json_normalize
Kinda hacky and requires a bit of RAM. But works, albeit naively.

Tested with Yelp JSON files in dataset challenge round 12:
https://www.yelp.com/dataset/challenge
'''

import json

Nov05

Find the elements that appear in both lists.

import time
with open('names_1.txt', 'r') as f:
    names_1 = f.read().split("\n")  # List containing 10000 names
with open('names_2.txt', 'r') as f:
    names_2 = f.read().split("\n")  # List containing 10000 names

Nov05

import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision.models as models


class EncoderCNN(nn.Module):
    def __init__(self, embed_size):
        # super(EncoderCNN, self).__init__()
        super().__init__()