yashprakash13

[tool.black]
line-length = 109
target-version = ['py37']

[tool.isort]
profile = "black"

yashprakash13

repos:
-   repo: https://github.com/pre-commit/pre-commit-hooks
    rev: v2.3.0
    hooks:
    -   id: check-yaml
    -   id: end-of-file-fixer
    -   id: trailing-whitespace
-   repo: https://github.com/psf/black
    rev: 21.12b0
    hooks:

yashprakash13

import argparse
import os
from train import train_cnn


# let's define some default hyperparameter values
PROJECT_NAME = "fashion_mnist"
BATCH_SIZE = 32
DROPOUT = 0.2
EPOCHS = 20

yashprakash13

"""
Defines a simple CNN model on the fashion mnist dataset.
"""

from keras.preprocessing.image import ImageDataGenerator
from keras.datasets import fashion_mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dropout, Dense, Flatten
from tensorflow.keras.optimizers import Adam
from keras.utils import np_utils

yashprakash13

study = optuna.create_study(direction="minimize")
study.optimize(objective, n_trials=500)

print(f"Optimized RMSE: {study.best_value:.4f}")
print("Best params:")
for key, value in study.best_params.items():
    print(f"\t{key}: {value}")

yashprakash13

def objective(n_trials):
  params = {
        "n_estimators": n_trials.suggest_int("n_estimators", 100, 2000, step=100),
        "learning_rate": n_trials.suggest_float("learning_rate", 1e-4, 0.3, log=True),
        "max_depth": n_trials.suggest_int("max_depth", 3, 15),
        "n_iter_no_change": 50,
    }
  dtrain = xgb.DMatrix(data = X_train, label = y_train)
  dval = xgb.DMatrix(data = X_test, label = y_val)

yashprakash13

from sklearn.model_selection import train_test_split

X = df.drop(columns=['median_house_value'])
y = df.median_house_value

# split the data
X_train, X_val, y_train, y_val = train_test_split(X, y,  test_size=0.2, random_state=0)
X_train.shape, X_val.shape, y_train.shape, y_val.shape

# make a new regressor model 

yashprakash13

# Do grid search

from sklearn.model_selection import GridSearchCV

rf_classifier = RandomForestClassifier(random_state=0)

rf_model_pipeline = Pipeline(steps=[
    ('preprocessing', columns_transformer),
    ('rf_model', rf_classifier),
])

yashprakash13

# MODEL Pipeline

from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix, accuracy_score
import matplotlib.pyplot as plt

# random forest classifier
rf_classifier = RandomForestClassifier(n_estimators = 11, criterion='entropy', random_state=0)

rf_model_pipeline = Pipeline(steps=[

yashprakash13

# COLUMN PIPELINE

from sklearn.impute import SimpleImputer
from sklearn.preprocessing import MinMaxScaler
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
›

col_transformation_pipeline = Pipeline(steps=[
    ('impute', SimpleImputer(strategy='mean')),