sksoumik

# mount gdrive
from google.colab import drive
drive.mount('/content/drive')

import pandas as pd 
import matplotlib.pyplot as plt
import numpy as np

import warnings
warnings.filterwarnings("ignore")

sksoumik

import tensorflow as tf
import torch 

device_name = tf.test.gpu_device_name()
if device_name != '/device:GPU:0':
  raise SystemError('GPU device not found')
print('Found GPU at: {}'.format(device_name))

>>> torch.cuda.get_device_name(0)

sksoumik

print('average sentence length: ', df.Text.str.split().str.len().mean())
print('stdev sentence length: ', df.Text.str.split().str.len().std())

sksoumik

import cv2 as cv 
import glob
import matplotlib.pyplot as plt 

path = "static/subfolder/*/*.jpg"

my_image_list = []

for file in glob.glob(path):
    file = cv.imread(file) # BGR

sksoumik

gpu_options = tf.compat.v1.GPUOptions(allow_growth=True)
session = tf.compat.v1.InteractiveSession(
    config=tf.compat.v1.ConfigProto(gpu_options=gpu_options)
)

sksoumik

data['target_column'].value_counts().plot.bar();

sksoumik

def sampling_k_elements(group, k=3):
    if len(group) < k:
        return group
    return group.sample(k)

balanced = df.groupby('class').apply(sampling_k_elements).reset_index(drop=True)

sksoumik

def sampling_k_elements(group, k=3):
    if len(group) < k:
        return group
    return group.sample(k)

balanced = df.groupby('class').apply(sampling_k_elements).reset_index(drop=True)

sksoumik

import sys

# put your output data container
print(report)

original_stdout = sys.stdout

with open("classification_report.txt", "w") as f:
    sys.stdout = f
    # put your output data container again

sksoumik

# check if there is any null values
df.isnull().sum()
# remove null values in aany rows
df = df.dropna(how='any',axis=0)
# check again if there is any null values
df.isnull().sum()