vikramsoni2

import matplotlib.pyplot as plt


def plot_graphs(history, string):
  plt.plot(history.history[string])
  plt.plot(history.history['val_'+string])
  plt.xlabel("Epochs")
  plt.ylabel(string)
  plt.legend([string, 'val_'+string])
  plt.show()

vikramsoni2

from zipfile import ZipFile
import os
from os.path import basename

def zip_dir(dirname, zipfilename):
    with ZipFile(zipfilename, 'w') as zipObj:
        # Iterate over all the files in directory
        for folderName, subfolders, filenames in os.walk(dirname):
            for filename in filenames:
                #create complete filepath of file in directory

vikramsoni2

import numpy as np
import pandas as pd
from matplotlib.path import Path
import matplotlib.pyplot as plt
import matplotlib.patches as patches
import seaborn as sns

from typing import Union, List, Tuple

def parallel_coordinates(df: pd.DataFrame, 

vikramsoni2

def top_10_accuracy(preds, train_data, is_higher_better=True):
    y_preds = np.asarray(preds).reshape(-1, len(np.unique(y)))
    y_true = train_data.get_label()
    score =  top_k_accuracy_score(y_true, y_preds, k=10)
    return ('top_10_accuracy', score, True)

vikramsoni2

import logging
from bisect import bisect
from logging import getLogger, Formatter, LogRecord, StreamHandler
from typing import Dict


class LevelFormatter(Formatter):
    def __init__(self, formats: Dict[int, str], **kwargs):
        super().__init__()

vikramsoni2

from requests import get
from io import BytesIO
from zipfile import ZipFile
import os
from pathlib import Path


destination = "testproject"
file_url = 'https://github.com/vikramsoni2/aihubcli/archive/refs/heads/main.zip'

vikramsoni2

metrics_names = ['loss', 'accuracy', 'top10_accuracy']

plt.figure(figsize=(14,4))
sns.set_style('whitegrid')
for i in range(len(metrics_names)):
    ax = plt.subplot(1, len(metrics_names), i+1)
    ax.plot(history.history[metrics_names[i]], label="train")
    ax.plot(history.history['val_'+ metrics_names[i]], label="valid")
    ax.title.set_text(metrics_names[i])
    

vikramsoni2

contractions = { 
"ain't": "am not",
"aren't": "are not",
"can't": "cannot",
"can't've": "cannot have",
"'cause": "because",
"could've": "could have",
"couldn't": "could not",
"couldn't've": "could not have",
"didn't": "did not",

vikramsoni2

def remove_highly_correlated_features(df = None, ths=0.99):
    print("The data has : {} features ".format(len(list(df))))
    correlations = df.corr()
    mask = np.triu(np.ones_like(correlations, dtype=bool))    
    corr_matrix = correlations.abs()
    # Create a True/False mask and apply it
    mask = np.triu(np.ones_like(corr_matrix, dtype=bool))
    tri_df = corr_matrix.mask(mask)
    # List column names of highly correlated features (r >0.98 )
    to_drop = [c for c in tri_df.columns if any(tri_df[c] > ths)]

vikramsoni2

y_true = le.inverse_transform(y_valid)
y_pred = le.inverse_transform(y_valid_pred_lr)

from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline


data = confusion_matrix(y_true, y_pred)