I'm trying to test several families, using different algorithms to see if any perform well. And I want to compare AUC with Standard Deviation using cross-validation with K-Fold.
X = pd.concat([X_train, X_test])
y = pd.concat([y_train, y_test])
from sklearn import model_selection
from sklearn.dummy import DummyClassifier
from sklearn.linear_model import (
LogisticRegression,
)
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import (
KNeighborsClassifier,
)
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.ensemble import (
RandomForestClassifier,
)
import xgboost
for model in [
DummyClassifier,
LogisticRegression,
DecisionTreeClassifier,
KNeighborsClassifier,
GaussianNB,
SVC,
RandomForestClassifier,
xgboost.XGBClassifier,
]:
cls = model()
kfold = model_selection.KFold(
n_splits=10, random_state=42
)
s = model_selection.cross_val_score(
cls, X, y, scoring="roc_auc", cv=kfold
)
print(
f"{model.__name__:22} AUC: "
f"{s.mean():.3f} STD: {s.std():.2f}"
)
ValueError: Setting a random_state has no effect since shuffle is False. You should leave random_state to its default (None), or set shuffle=True.
Thank you for your help
Related
I have a question for those who have some experience with timeseries forecasting.
I have been experiment with this field for few weeks and i was trying to forecast some timeseries with both ARIMA and LSTM models to compare the results.
Basically i did plot this graph Figure 1 that has 4 plots :
Top left : ARIMA training data points and fitted model points.
Top right : ARIMA test and forecast points.
Bottom Left : LSTM training data and fitted data (i could not really find fitted point for LSTM so i just forecasted the training data but you can just ignore that part).
Bottom right : Test and forecast data for the LSTM model.
This graph was acceptable and also i did compute the RMSE and MSE and LSTM gave lower error which agrees with most literature online that states the superiority of LSTM over ARIMA models.
However after i did plot the loss and validation loss of the LSTM model to have more insights, i noticed that the validation_loss is following a wierd flectuating pattern Figure 2.
I can explain this as follow : the time series has a lot of outliers or abnormal behaviour, so splitting it to train/validation/test would mean validation cannot be really a good metric to show how good the model can learn.
But since all research papers never show this graph and explain this problem, i don't have a solid argument to defende this idea.
what do you guys think?
Thank you in advance
import pandas as pd
import matplotlib.pyplot as plt
from statsmodels.tsa.stattools import adfuller
from statsmodels.graphics.tsaplots import plot_acf,plot_pacf
import statsmodels.api as sm
from statsmodels.tsa.arima.model import ARIMA
from sklearn.metrics import r2_score,mean_squared_error,mean_absolute_percentage_error,mean_absolute_percentage_error
from statsmodels.tsa.seasonal import STL
import numpy as np
from pandas import Series, DataFrame
from scipy import stats
from statsmodels.tsa.stattools import adfuller
import statsmodels
from statsmodels.tsa.seasonal import seasonal_decompose
from pandas.plotting import register_matplotlib_converters
import pmdarima as pm
register_matplotlib_converters()
import warnings
import time
from numpy import array
from keras.models import Sequential
from keras.layers import LSTM
from keras.layers import Dense
from numpy import array
import keras_tuner as kt
import tensorflow as tf
print(tf.__version__)
from numpy import array
from tensorflow import keras
import keras_tuner as kt
from sklearn.preprocessing import MinMaxScaler
from keras.layers import Bidirectional
from keras.models import Sequential
from keras.preprocessing.sequence import TimeseriesGenerator
from keras.layers import Bidirectional
from tensorflow.keras import initializers
import random as rn
np.random.seed(123)
rn.seed(123)
tf.random.set_seed(123)
tf.keras.utils.set_random_seed(123)
keras.utils.set_random_seed(123)
warnings.filterwarnings('ignore')
df3 = pd.read_csv('favorita_train.csv')
## 1 - Get TS and do STL
print("TS lenbgth : "+str(len(df3)))
results = seasonal_decompose(df3['unit_sales'],period=30)
results.plot();
train_all = df3.iloc[:int(len(df3)*0.8)]
train = df3.iloc[:int(len(df3)*0.6)]
val = df3.iloc[int(len(df3)*0.6):int(len(df3)*0.8)]
test = df3.iloc[int(len(df3)*0.8):]
scaler = MinMaxScaler()
scaler.fit(train_all)
scaled_all = scaler.transform(df3)
scaled_train = scaler.transform(train)
scaled_train_all = scaler.transform(train_all)
scaled_val = scaler.transform(val)
scaled_test = scaler.transform(test)
# We do the same thing, but now instead for 12 months
n_features = 1
n_input =5
train_generator_all = TimeseriesGenerator(scaled_train_all, scaled_train_all, length=n_input, batch_size=1,shuffle=True)
train_generator = TimeseriesGenerator(scaled_train, scaled_train, length=n_input, batch_size=1,shuffle=True)
val_generator = TimeseriesGenerator(scaled_val, scaled_val, length=n_input, batch_size=1,shuffle=True)
adfPValue = adfuller(scaled_all)
adfPValue=adfPValue[1]
adi = len(scaled_all)/((scaled_all != 0).sum())
sd=scaled_all.std()
mean=scaled_all.mean()
cv2 = np.square(sd/mean)
print("CV2 (describe magnitude of demande variability <0.5 is good) :"+str(cv2))
print("SD (-2,2 is good | mean data variance is low) :"+str(sd))
print("ADI (1.3 or smaller means smooth ts) :"+str(adi))
print("Stationarity test (stationary if <0.05) :"+str(adfPValue))
def model_builder(hp):
model = keras.Sequential()
hp_units = hp.Int('units', min_value=1, max_value=50, step=1)
hp_layers = hp.Int('layers', min_value=1, max_value=3, step=1)
if hp_layers==1 :
model.add(Bidirectional(LSTM(hp_units,activation='relu'), input_shape=(n_input, n_features)))
elif hp_layers==2:
model.add(Bidirectional(LSTM(hp_units, activation='relu', return_sequences=True), input_shape=(n_input, n_features)))
model.add(Bidirectional(LSTM(hp_units, activation='relu')))
else:
model.add(Bidirectional(LSTM(hp_units, activation='relu', return_sequences=True), input_shape=(n_input, n_features)))
for i in range(hp_layers-2):
model.add(Bidirectional(LSTM(hp_units, activation='relu', return_sequences=True)))
model.add(Bidirectional(LSTM(hp_units, activation='relu')))
model.add(Dense(1))
hp_learning_rate = hp.Choice('learning_rate', values=[1e-2, 1e-3, 1e-4])
model.compile(optimizer=keras.optimizers.Adam(learning_rate=hp_learning_rate), loss='mse',metrics=['accuracy'])
return model
tuner = kt.Hyperband(model_builder,
objective='val_loss',
max_epochs=300,
factor=3,
directory='499',
project_name='949',
seed=123)
stop_early = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=30)
tuner.search(train_generator, epochs=300, validation_data=val_generator, shuffle=True, callbacks=[stop_early], batch_size=len(train_generator))
best_hps=tuner.get_best_hyperparameters(num_trials=1)[0]
print(best_hps.get('units'))
print(best_hps.get('layers'))
print(best_hps.get('window'))
print(best_hps.get('learning_rate'))
best_hps=tuner.get_best_hyperparameters(num_trials=1)[0]
model = tuner.hypermodel.build(best_hps)
history = model.fit(img_train, label_train, epochs=50, validation_split=0.2)
val_acc_per_epoch = history.history['val_accuracy']
best_epoch = val_acc_per_epoch.index(max(val_acc_per_epoch)) + 1
print('Best epoch: %d' % (best_epoch,))
I am practicing with this life expectancy dataset from Kaggle (https://www.kaggle.com/datasets/kumarajarshi/life-expectancy-who?select=Life+Expectancy+Data.csv) and I want to train and visualize a classification and regression tree model. however, I keep getting an error that says "InvocationException: GraphViz's executables not found". I am wondering if this is because of the nature of the continuous numerical target dataset type? how can I visualize the model?
code:
import warnings
warnings.filterwarnings('ignore')
import pandas as pd
import numpy as np
import seaborn as sn
from sklearn import datasets
from sklearn import metrics
from sklearn import tree
from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import DecisionTreeRegressor
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder
from sklearn.tree import export_graphviz
import matplotlib.pyplot as plt,pydotplus
from IPython.display import Image,display
data = pd.read_csv('Life Expectancy Data.csv')
data = data.dropna(how = 'any')
#feature selection
data = data.drop(columns=['infant deaths', ' thinness 5-9 years', 'Alcohol', 'percentage expenditure', 'Hepatitis B', 'Total expenditure', 'Population', ' thinness 5-9 years', 'Year', 'Country'])
# Creating a instance of label Encoder.
le = LabelEncoder()
# Using .fit_transform function to fit label
# encoder and return encoded label
label = le.fit_transform(data['Status'])
# removing the column 'Status' from df
data.drop('Status', axis=1, inplace=True)
# Appending the array to our dataFrame
# with column name 'Status'
data['Status'] = label
#training model
model_data = data
X = data.drop(columns=['Life expectancy '])
y = data['Life expectancy ']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)
model = DecisionTreeRegressor()
model.fit(X_train, y_train)
#visualizing tree
LEtree = tree.export_graphviz(model,
feature_names = ['Adult Mortality', 'Measles', ' BMI', 'under-five deaths', 'Polio', 'Diphtheria', ' HIV/AIDS', 'GDP', ' thinness 1-19 years', 'Income composition of resources', 'Schooling', 'Status'],
class_names = y,
label = 'all',
rounded = True,
filled = True)
graph=pydotplus.graph_from_dot_data(LEtree)
display(Image(graph.create_png()))
full error message:
InvocationException Traceback (most recent call last)
Input In [27], in <cell line: 2>()
1 graph=pydotplus.graph_from_dot_data(LEtree)
----> 2 display(Image(graph.create_png()))
File ~\Anaconda3\lib\site-packages\pydotplus\graphviz.py:1797, in Dot.__init__.<locals>.<lambda>(f, prog)
1792 # Automatically creates all the methods enabling the creation
1793 # of output in any of the supported formats.
1794 for frmt in self.formats:
1795 self.__setattr__(
1796 'create_' + frmt,
-> 1797 lambda f=frmt, prog=self.prog: self.create(format=f, prog=prog)
1798 )
1799 f = self.__dict__['create_' + frmt]
1800 f.__doc__ = (
1801 '''Refer to the docstring accompanying the'''
1802 ''''create' method for more information.'''
1803 )
File ~\Anaconda3\lib\site-packages\pydotplus\graphviz.py:1959, in Dot.create(self, prog, format)
1957 self.progs = find_graphviz()
1958 if self.progs is None:
-> 1959 raise InvocationException(
1960 'GraphViz\'s executables not found')
1962 if prog not in self.progs:
1963 raise InvocationException(
1964 'GraphViz\'s executable "%s" not found' % prog)
InvocationException: GraphViz's executables not found
Try Installing the Graphviz in a proper directory
you can install in Anaconda from conda-command-prompt using the below command -
conda install -c conda-forge python-graphviz
and replace the previously installed graphviz directory this might help you with the problem
First of all, thank you for allowing me to use this wonderful library
I am doing Korean NLP now
So I pre-processed Korean and converted it into a Tfidf Vectorizer.
I'm going to put it in setup() and use it, but there are errors
Can't I use the sparse matrix for the pycaret?
If so, is there any way to do Korean NLP?
X_train = train_data.Text.tolist()
Y_train =train_data['Label'].values
X_test = test_data.Text.tolist()
Y_test =test_data['Label'].values
from soynlp.word import WordExtractor
word_extractor = WordExtractor(min_frequency=100,
min_cohesion_forward=0.05,
min_right_branching_entropy=0.0
)
word_extractor.train(X_train) # list of str or like
words = word_extractor.extract()
scores = word_extractor.word_scores()
import math
score_dict = {key: scores[key].cohesion_forward *
math.exp(scores[key].right_branching_entropy)
for key in scores}
from soynlp.tokenizer import LTokenizer
cohesion_score = {word:score.cohesion_forward for word, score in words.items()}
tokenizer = LTokenizer(scores=score_dict)
import os
from scipy.sparse import save_npz, load_npz
from sklearn.feature_extraction.text import TfidfVectorizer
# if not os.path.isfile('soy_train.npz'):
tfidf = TfidfVectorizer(ngram_range=(1, 2),
min_df=3,
tokenizer=tokenizer.tokenize,
token_pattern=None)
tfidf.fit(X_train)
X_train_soy = tfidf.transform(X_train)
X_test_soy = tfidf.transform(X_test)
save_npz('soy_train.npz', X_train_soy)
save_npz('soy_test.npz', X_test_soy)
type(X_train_soy[0])
import numpy as np
train = pd.DataFrame(X_train_soy)
y_train = np.array(Y_train,dtype=float)
train['Label'] = y_train
from pycaret.classification import *
import numpy as np
exp1 = setup(train,train_size=0.8, target = 'Label',use_gpu = True)
TypeError: Cannot compare types 'ndarray(dtype=object)' and 'float'
When doing df = gpd.GeoDataFrame(df1, crs = 'EPSG:4326', geometry = geopandas.points_from_xy(df1.longitude,df1.latitude)) I get "name 'pygeos' is not defined", yet I have installed pygeos in the directory where I dev and
python3.9/site-packages/geopandas/_vectorized.py in points_from_xy(x, y, z)
247
248 if compat.USE_PYGEOS:
--> 249 return pygeos.points(x, y, z)
250 else:
251 out = _points_from_xy(x, y, z)
anf import pygeos is in the script. Is there a specific way to well install pygeos in order to avoid such error ? Thanks
USE_PYGEOS=1
import pyproj
import shapely
import pandas as pd
pd.options.display.max_rows = 100
import geopandas as gpd
import numpy as np
import sklearn
import matplotlib.pyplot as plt
gpd.show_versions()
print(gpd.options.use_pygeos)
location_df = pd.read_csv("location_01-03_01-04.csv", sep = ";")
import rtree
import pygeos
gpd.options.use_pygeos = True
#Point is (longitude, latitude)
# Function making geopandas points of latitude, longitude
location_geo = gpd.GeoDataFrame(location_df, crs = 'EPSG:4326', geometry = gpd.points_from_xy(location_df.longitude, location_df.latitude))
departments_df = gpd.read_file("departements.geojson", sep = ";")
print(departments_df)
import time
start = time.time()
print("hello")
import geopandas
import rtree
# Function to check wether a department contains a position - returns the department of the position. NaN values are probably in another country
dept_points = geopandas.sjoin(location_geo, departments_df)
end = time.time()
print(end-start, ' s')
print(dept_points)
Somehow this did it for me.
It was about setting the constant and importing packages in a specific order.
I used transfer learning to train the model. The fundamental model was efficientNet.
You can read more about it here
from tensorflow import keras
from keras.models import Sequential,Model
from keras.layers import Dense,Dropout,Conv2D,MaxPooling2D,
Flatten,BatchNormalization, Activation
from keras.optimizers import RMSprop , Adam ,SGD
from keras.backend import sigmoid
Activation function
class SwishActivation(Activation):
def __init__(self, activation, **kwargs):
super(SwishActivation, self).__init__(activation, **kwargs)
self.__name__ = 'swish_act'
def swish_act(x, beta = 1):
return (x * sigmoid(beta * x))
from keras.utils.generic_utils import get_custom_objects
from keras.layers import Activation
get_custom_objects().update({'swish_act': SwishActivation(swish_act)})
Model Definition
model = enet.EfficientNetB0(include_top=False, input_shape=(150,50,3), pooling='avg', weights='imagenet')
Adding 2 fully-connected layers to B0.
x = model.output
x = BatchNormalization()(x)
x = Dropout(0.7)(x)
x = Dense(512)(x)
x = BatchNormalization()(x)
x = Activation(swish_act)(x)
x = Dropout(0.5)(x)
x = Dense(128)(x)
x = BatchNormalization()(x)
x = Activation(swish_act)(x)
x = Dense(64)(x)
x = Dense(32)(x)
x = Dense(16)(x)
# Output layer
predictions = Dense(1, activation="sigmoid")(x)
model_final = Model(inputs = model.input, outputs = predictions)
model_final.summary()
I saved it using:
model.save('model.h5')
I get the following error trying to load it:
model=tf.keras.models.load_model('model.h5')
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-12-e3bef1680e4f> in <module>()
1 # Recreate the exact same model, including its weights and the optimizer
----> 2 model = tf.keras.models.load_model('PhoneDetection-CNN_29_July.h5')
3
4 # Show the model architecture
5 model.summary()
10 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/generic_utils.py in class_and_config_for_serialized_keras_object(config, module_objects, custom_objects, printable_module_name)
319 cls = get_registered_object(class_name, custom_objects, module_objects)
320 if cls is None:
--> 321 raise ValueError('Unknown ' + printable_module_name + ': ' + class_name)
322
323 cls_config = config['config']
ValueError: Unknown layer: FixedDropout
```python
I was getting the same error while trying to do the inference by loading my saved model.
Then i just imported the effiecientNet library in my inference notebook as well and the error was gone.
My import command looked like:
import efficientnet.keras as efn
(Note that if you havent installed effiecientNet already(which is unlikely), you can do so by using !pip install efficientnet command.)
I had this same issue with a recent model. Researching the source code you can find the FixedDropout Class. I added this to my inference code with import of backend and layers. The rate should also match the rate from your efficientnet model, so for the EfficientNetB0 the rate is .2 (others are different).
from tensorflow.keras import backend, layers
class FixedDropout(layers.Dropout):
def _get_noise_shape(self, inputs):
if self.noise_shape is None:
return self.noise_shape
symbolic_shape = backend.shape(inputs)
noise_shape = [symbolic_shape[axis] if shape is None else shape
for axis, shape in enumerate(self.noise_shape)]
return tuple(noise_shape)
model = keras.models.load_model('model.h5',
custom_objects={'FixedDropout':FixedDropout(rate=0.2)})
I was getting the same error. Then I import the below code. then it id working properly
import cv2
import matplotlib.pyplot as plt
import tensorflow as tf
from sklearn.metrics import confusion_matrix
import itertools
import os, glob
from tqdm import tqdm
from efficientnet.tfkeras import EfficientNetB4
if you don't have to install this. !pip install efficientnet. If you have any problem put here.
In my case, I had two files train.py and test.py.
I was saving my .h5 model inside train.py and was attempting to load it inside test.py and got the same error. To fix it, you need to add the import statements for your efficientnet models inside the file that is attempting to load it as well (in my case, test.py).
from efficientnet.tfkeras import EfficientNetB0