tiaplagata

from sklearn.metrics import recall_score, make_scorer

# Define the pipeline
pipeline = Pipeline(steps= [
                    ("ColumnTransformer", SelectColumnsTransformer(columns=features_to_use)),
                    ("TransformCategorical", Transform_Categorical()),
                    ("SMOTE", SMOTE()),
                    ("GradientBooster", GradientBoostingClassifier())
                    ])

tiaplagata

from sklearn.preprocessing import FunctionTransformer

# The function we want to convert to a class for our pipeline
def transform_yes_no(X):
  X['international plan'] = X['international plan'].apply(lambda x: 1 if x.lower() == 'yes' else 0)
  X['voice mail plan'] = X['voice mail plan'].apply(lambda x: 1 if x.lower() == 'yes' else 0)
  return X

# Convert to class for pipeline
YesNoTransformer = FunctionTransformer(transform_yes_no)

tiaplagata

from google.colab import drive
import os

# Mount Google Drive
drive.mount('/gdrive', force_remount=True)

# Location of Zip File
drive_path = '/gdrive/MyDrive/Data/pneumonia_data.zip'
local_path = '/content'

tiaplagata

from tensorflow.keras.preprocessing.image import ImageDataGenerator

# Create data generators
# File path = path to train/test/val folders respectively
# Use a target size of 224x224 px for each image (or whatever size you choose)
# Batch size = total number of images in the train set, test set, val set respectively
# Ensure class_mode is binary
train_generator = ImageDataGenerator(rescale=1./255).flow_from_directory(
                                                    '/content/chest_xray/train',
                                                     target_size=(224, 224),

tiaplagata

from wordcloud import WordCloud, ImageColorGenerator
from PIL import Image
import matplotlib.pyplot as plt

import pandas as pd
import numpy as np

tiaplagata

#Give our Rome corpus a variable name
rome_corpus = df.lemmatized[10]

#Instantiate wordcloud object and use method to feed it our corpus
wc = WordCloud().generate_from_text(rome_corpus)

#Use matplotlib.pyplot to display the fitted wordcloud
#Turn axis off to get rid of axis numbers
plt.imshow(wc)
plt.axis('off')

tiaplagata

# Store our document term matrix data for Rome 
data = dtm.transpose()['Rome, Italy'].sort_values(ascending=False)

# Generate the word cloud from frequencies
wc = WordCloud().generate_from_frequencies(data)

plt.imshow(wc)
plt.axis('off')
plt.show()

tiaplagata

#Define a list of stop words
stopwords = ['private', 'tour', 'transfer', 'guide', 'skip', 'line',
             'skiptheline', 'vice', 'versa']

#A function to generate the word cloud from text
def generate_basic_wordcloud(data, title):
    cloud = WordCloud(width=400,
                      height=330,
                      max_words=150,
                      colormap='tab20c',

tiaplagata

# Create an array from the image you want to use as a mask
## Your file path will look different
rome_mask = np.array(Image.open('/Users/tiaplagata/Downloads/italy.jpg'))

tiaplagata

# A similar function, but using the mask
def generate_better_wordcloud(data, title, mask=None):
    cloud = WordCloud(scale=3,
                      max_words=150,
                      colormap='RdYlGn',
                      mask=mask,
                      background_color='white',
                      stopwords=stopwords,
                      collocations=True).generate_from_text(data)
    plt.figure(figsize=(10,8))