nmolivo

import matplotlib.pyplot as plt
from numpy.random import normal, uniform
import pandas as pd
import os
os.listdir()

data = pd.read_csv("DSI.csv")

data.head()

nmolivo

scores = cross_val_score(LinearRegression(), Xr, yr, cv=397, scoring = "r2")
print("Cross-validated scores:", scores)
print("Average: ", scores.mean())
print("Variance: ", np.std(scores))

nmolivo

loo = LeaveOneOut()
ytests = []
ypreds = []
for train_idx, test_idx in loo.split(Xr):
    X_train, X_test = X_array[train_idx], X_array[test_idx] #requires arrays
    y_train, y_test = y_array[train_idx], y_array[test_idx]
    
    model = LinearRegression()
    model.fit(X = X_train, y = y_train) 
    y_pred = model.predict(X_test)

nmolivo

mapping_dict ={}
for i, img_url in enumerate(image_list[0:10000]):
    img_name = "img_%05d" % (i,)
    mapping_dict[img_name] = img_url
    
    if (img_url == np.nan) | (str(img_url) == "nan"):
        continue
    else:
        # Uses the creds in ~/.aws/credentials
        s3_image_filename = img_name

nmolivo

# http://docs.aws.amazon.com/rekognition/latest/dg/get-started-exercise.html
fileName='img_00001'
bucket='bucket_name'
client=boto3.client('rekognition')
## ^^ we only need to do this code once for the following examples. I include it 
##    re-instated in case you want to check out different pics.

response = client.detect_labels(Image={'S3Object':{'Bucket':bucket,'Name':fileName}},MinConfidence=75)
response

nmolivo

fileName= 'img_00006'
bucket='bucket_name'

text_in_image = client.detect_text(Image={'S3Object':{'Bucket':bucket,'Name':fileName}})
text_in_image["TextDetections"]

nmolivo

fileName= 'img_00012'
bucket='bucket_name'

celeb_detect = client.recognize_celebrities(Image={'S3Object':{'Bucket':bucket,'Name':fileName}})
celeb_detect["CelebrityFaces"]

nmolivo

bucket_name = 'bucket_name'
s3 = boto3.resource('s3')
bucket = s3.Bucket(bucket_name)
images = [img.key for img in bucket.objects.all()] #fetches image names from your S3 bucket
client = boto3.client('rekognition')

results_wide = []
results_long = []

for img in images:

nmolivo

model_data['activity'] = model_data['Activity'].map({'Scuba Diving':'Diving', 'Scuba diving':'Diving','2 boats capsized': 'Disaster','Treading water': 'Swimming',
                         'Air Disaster': 'Disaster','Surfing': 'Surfing', 'Night bathing': 'Swimming', 'Snorkeling': 'Swimming','Measuring sharks': 'Handling',
                         'Swimming': 'Swimming', 'Surfing': 'Surfing', 'Kayaking / Fishing': 'Fishing','Body surfing': 'Surfing', 'Fishing': 'Fishing', 
                         'Spearfishing': 'Spear Fishing','Swimming, poaching abalone': 'Diving', 'Wading': 'Shallow Water', 'Canoeing': 'Rowing', 
                         'Feeding sharks': 'Handling', 'Paddle boarding':'Rowing','SUP':'Rowing','Body boarding':'Surfing', 'Touching a shark': 'Handling',
                         'Attempting to lasso a shark':'Handling','Surfing ':'Surfing','Tagging sharks':'Handling', 'Kakaying': 'Rowing','Washing hands':'Fishing',
                         'Grabbing shark for a selfie': 'Handling', 'Kayak fishin

nmolivo

import os
import pandas as pd
from time import sleep

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.firefox.firefox_binary import FirefoxBinary