TomHortons

from __future__ import print_function
import httplib2
import os

from apiclient import discovery
from oauth2client import client
from oauth2client import tools
from oauth2client.file import Storage

try:

TomHortons

from skimage import io
image_paths = sorted(glob('../input/train-tif/*.tif'))[0:1000]
image_paths_jpg = sorted(glob('../input/train-jpg/*.jpg'))[0:1000]
imgs = [io.imread(path) / io.imread(path).max() for path in image_paths]
#r, g, b, nir = img[:, :, 0], img[:, :, 1], img[:, :, 2], img[:, :, 3]
ndvis = [(img[:,:,3] - img[:,:,0])/((img[:,:,3] + img[:,:,0])) for img in imgs]

n = 16
plt.figure(figsize=(12,8))
plt.subplot(131)

TomHortons

from sklearn.manifold import TSNE
tsne = TSNE(
    n_components=2,
    init='random', # pca
    random_state=101,
    method='barnes_hut',
    n_iter=500,
    verbose=2
).fit_transform(img_mat)

TomHortons

mask = np.zeros_like(sq_dists, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True

# upper triangle of matrix set to np.nan
sq_dists[np.triu_indices_from(mask)] = np.nan
sq_dists[0, 0] = np.nan

fig = plt.figure(figsize=(12,8))
# maximally dissimilar image
ax = fig.add_subplot(1,2,1)

TomHortons

%matplotlib inline
import plotly.offline as py
py.init_notebook_mode(connected=True)
import plotly.graph_objs as go
import plotly.tools as tls

from sklearn.manifold import TSNE
tsne = TSNE(
    n_components=3,
    init='random', # pca

TomHortons

import cv2

n_imgs = 600

all_imgs = []

for i in range(n_imgs):
    img = plt.imread(image_paths[i])
    img = cv2.resize(img, (100, 100), cv2.INTER_LINEAR).astype('float')
#    img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY).astype('float')

TomHortons

from sklearn.multiclass import OneVsRestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV, train_test_split
from sklearn.preprocessing import MultiLabelBinarizer, MinMaxScaler
from sklearn.metrics import fbeta_score, precision_score, make_scorer, average_precision_score
import cv2
import warnings

n_samples = 5000
rescaled_dim = 20

TomHortons

# Co-occurence Matrix
com = np.zeros([len(counts)]*2)
for i, l in enumerate(list(counts.keys())):
    for i2, l2 in enumerate(list(counts.keys())):
        c = 0
        cy = 0
        for row in labels.values:
            if l in row:
                c += 1
                if l2 in row: cy += 1

TomHortons

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import os
import gc
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

pal = sns.color_palette()

TomHortons

# -*- coding: utf-8 -*-
"""
Thanks to tinrtgu for the wonderful base script
Use pypy for faster computations.!
"""
import csv
from datetime import datetime
from csv import DictReader
from math import exp, log, sqrt