hamletbatista

document.querySelector('#yDmH0d > c-wiz:nth-child(21) > div > div.OoO4Vb > span > div > div.y3IDJd.rFZTte.Fx3kmc > content > div.shSP > div > div > div.LgQiCc.vOSR6b.RVNZdd.qtMyGd > content > div.khfFee > div > div.CC5fre')

hamletbatista

import pandas as pd

#example list of urls to inspect
site_pages = ["https://www.ranksense.com/", "https://www.ranksense.com/how-it-works/", 
              "https://www.ranksense.com/pricing/", "https://www.ranksense.com/blog/", 
              "https://www.ranksense.com/products/organic-search-ads/feed/",
              "https://www.ranksense.com/additional-ways-to-use-chrome-developer-tools-for-seo/",
              "https://www.ranksense.com/empowering-a-new-generation-of-seos-with-python/"]

data = asyncio.get_event_loop().run_until_complete(inspect_urls(site_pages))

hamletbatista

import sklearn as sk
from bs4 import BeautifulSoup

img_counts = pd.read_csv("/content/gdrive/My Drive/img_sizes.csv", usecols=["url", "img_src", "filesize", "width", "height"])
form_counts = pd.read_csv("/content/gdrive/My Drive/form_counts.csv", usecols=["url", "form_count", "input_count"])]

form_counts.head().drop("url", axis=1)
#outputs example data

img_counts.drop(["url", "img_src"], axis=1).head()

hamletbatista

def img_size_group(size):
  max_size = 50000
  #image size bins
  img_size_groups = [i for i in 
                      zip(
                        [i for i in range(0, max_size, 1000)], 
                        [i for i in range(1000, max_size, 1000)]
                      )
                    ]
  

hamletbatista

ml_data = form_counts.merge(onehot_img, on="url")

ml_data.loc[:, 'group'] = "N/A"
ml_data.loc[ml_data['url'].str.contains(r".*/products/.*|.*/product/.*"), "group"] = "Products"
ml_data.loc[ml_data['url'].str.contains(r"/collections(?!.*/products.*)(?!.*/product.*)"), "group"] = "Category"

#splitting dataset into training and testing
X_train, X_test, y_train, y_test = train_test_split(ml_data.drop(["group", "url"], axis=1), ml_data['group'], test_size=0.2, random_state=42)

hamletbatista

names = [
         "Naive Bayes",
         "Linear SVM",
         "Logistic Regression",
         "Random Forest",
         "Multilayer Perceptron"
        ]

classifiers = [
    MultinomialNB(),

hamletbatista

def plot_confusion_matrix(cm, classes,
                          normalize=False,
                          title='Confusion matrix',
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    Normalization can be applied by setting `normalize=True`.
    """
    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]

hamletbatista

results = pd.DataFrame(rows, columns=["algorithm", "score", "params"])
results = results.groupby("algorithm").max().reset_index()

plot_data = []

bar = go.Bar(
    y = results['score'].tolist(),
    x = results['algorithm'].tolist()
)

hamletbatista

import requests
from urllib.parse import urlencode, urlparse, urlunparse, quote
import pandas as pd

def get_seo_branded_data(brand, domain, database="us", export_columns="Ph,Po,Nq,Ur,Tg,Td,Ts", display_limit=10000, display_filter="+|Ph|Co|{brand}"):
  
  global key
  
  url_params={"type": "domain_organic",
             "key": key,

hamletbatista

database="us"
macys="macys.com"
brand="Tommy Hilfiger"

macys_df = get_seo_branded_data(brand, macys, export_columns="Ph,Po,Tg") # only keyword, position and traffic

#we explicitly convert numbers to integers to be able to perform arithmetic operations later
convert_dict = {'Keyword': str, 'Position': int, 'Traffic': int} 

macys_df = macys_df.astype(convert_dict)