I have a sample time-series dataset (23, 208), which is a pivot table count for 24hrs count for some users; I was experimenting with different regressors from sklearn which work fine (except for SGDRegressor()), but this LightGBM Python-package gives me very linear prediction as follows:
my tried code:
import pandas as pd
dff = pd.read_csv('ex_data2.csv',sep=',')
dff.set_index("timestamp",inplace=True)
print(dff.shape)
from sklearn.model_selection import train_test_split
trainingSetf, testSetf = train_test_split(dff,
#target_attribute,
test_size=0.2,
random_state=42,
#stratify=y,
shuffle=False)
import lightgbm as lgb
from sklearn.multioutput import MultiOutputRegressor
username = 'MMC_HEC_LVP' # select one column for plotting & check regression performance
user_list = []
for column in dff.columns:
user_list.append(column)
index = user_list.index(username)
X_trainf = trainingSetf.iloc[:,:].values
y_trainf = trainingSetf.iloc[:,:].values
X_testf = testSetf.iloc[:,:].values
y_testf = testSetf.iloc[:,:].values
test_set_copy = y_testf.copy()
model_LGBMRegressor = MultiOutputRegressor(lgb.LGBMRegressor()).fit(X_trainf, y_trainf)
pred_LGBMRegressor = model_LGBMRegressor.predict(X_testf)
test_set_copy[:,[index]] = pred_LGBMRegressor[:,[index]]
#plot the results for selected user/column
import matplotlib.pyplot as plt
plt.style.use("fivethirtyeight")
plt.figure(figsize=(12, 10))
plt.xlabel("Date")
plt.ylabel("Values")
plt.title(f"{username} Plot")
plt.plot(trainingSetf.iloc[:,[index]],label='trainingSet')
plt.plot(testSetf.iloc[:,[index]],"--",label='testSet')
plt.plot(test_set_copy[:,[index]],'b--',label='RF_predict')
plt.legend()
So what I am missing is if I use default (hyper-)parameters?
Short Answer
Your dataset has a very small number of rows, and LightGBM's parameters have default values set to provide good performance on medium-sized datasets.
Set the following parameters to force LightGBM to fit to the provided data.
min_data_in_bin = 1
min_data_in_leaf = 1
Long Answer
Before training, LightGBM does some pre-processing on the input data.
For example:
bundling sparse features
binning continuous features into histograms
dropping features which are guaranteed to be uninformative (for example, features which are constant)
The result of that preprocessing is a LightGBM Dataset object, and running that preprocessing is called Dataset "construction". LightGBM performs boosting on this Dataset object, not raw data like numpy arrays or pandas data frames.
To speed up construction and prevent overfitting during training, LightGBM provides ability to the prevent creation of histogram bins that are too small (min_data_in_bin) or splits that produce leaf nodes which match too few records (min_data_in_leaf).
Setting those parameters to very low values may be required to train on small datasets.
I created the following minimal, reproducible example, using Python 3.8.12, lightgbm==3.3.2, numpy==1.22.2, and scikit-learn==1.0.2 demonstrating this behavior.
from lightgbm import LGBMRegressor
from sklearn.metrics import r2_score
from sklearn.datasets import make_regression
# 20-row input data
X, y = make_regression(
n_samples=20,
n_informative=5,
n_features=5,
random_state=708
)
# training produces 0 trees, and predicts mean(y)
reg = LGBMRegressor(
num_boost_round=20,
verbosity=0
)
reg.fit(X, y)
print(f"r2 (defaults): {r2_score(y, reg.predict(X))}")
# 0.000
# training fits and predicts well
reg = LGBMRegressor(
min_data_in_bin=1,
min_data_in_leaf=1,
num_boost_round=20,
verbosity=0
)
reg.fit(X, y)
print(f"r2 (small min_data): {r2_score(y, reg.predict(X))}")
# 0.985
If you use LGBMRegressor(min_data_in_bin=1, min_data_in_leaf=1) in the code in the original post, you'll see predictions that better fit to the provided data.
In this way the model is overfitted!
If you do a random split after creating the dataset and evaluate the model on the test dataset, you will notice that the performance is essentially the same or worse (as in this example).
# SETUP
# =============================================================
from lightgbm import LGBMRegressor
from sklearn.metrics import r2_score
from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split
X, y = make_regression(
n_samples=200, n_informative=10, n_features=40, random_state=123
)
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.33, random_state=42
)
# =============================================================
# TEST 1
reg = LGBMRegressor(num_boost_round=20, verbosity=0)
reg.fit(X, y)
print(f"r2 (defaults): {r2_score(y, reg.predict(X))}")
# 0.815
reg = LGBMRegressor(
min_data_in_bin=1, min_data_in_leaf=1, num_boost_round=20, verbosity=0
)
reg.fit(X, y)
print(f"r2 (small min_data): {r2_score(y, reg.predict(X))}")
# 0.974
# =============================================================
# TEST 2
reg = LGBMRegressor(num_boost_round=20, verbosity=0)
reg.fit(X_train, y_train)
print(f"r2 (defaults): {r2_score(y_train, reg.predict(X_train))}")
# 0.759
reg = LGBMRegressor(
min_data_in_bin=1, min_data_in_leaf=1, num_boost_round=20, verbosity=0
)
reg.fit(X_train, y_train)
print(f"r2 (small min_data): {r2_score(y_test, reg.predict(X_test))}")
# 0.219
Related
I am trying to plot a feature importance plot that provides me with intuitive column names when it comes to their interpretation. Currently, I have a dataset mixed of numerical and 150+ categorical variables. None, of these categorical variables are ordinal. I attempted using get_dummies but I am worried about the dummy trap, speed due to too many resulting columns. How can I make this more efficient and accurate?
from sklearn.pipeline import Pipeline
from xgboost import XGBClassifier
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
#create dummies for all object features only and leave numerical column as is - ISSUE: RUNS FOR TOO LONG AND EVENTUALLY BREAKS!
X_encoded=pd.get_dummies(data=df, columns=df(['object']).columns)
# Define model
model = XGBClassifier()
pipeline = Pipeline([
("preprocessing", preprocessing_pipeline),
("classifier", model)
])
#test, train split
X_train, X_test, y_train, y_test = train_test_split(X_encoded, y, test_size=0.2, random_state=42, stratify=y_closed)
#fit
trained_pipeline = pipeline.fit(X_train, y_train)
#plot feature imp
%matplotlib inline
import matplotlib.pyplot as plt
N_FEATURES = 10 #top 10 only
feature_names = preprocessing_pipeline.transform(X_train.head(1)).columns
importances = model.feature_importances_
indices = np.argsort(importances)[-N_FEATURES:]
plt.figure(figsize=(15, 8))
plt.title('Feature Importances')
plt.show()
The issue is that the get_dummies runs for hours and eventually my kernel dies. How can this be optimized?
I recently discovered this amazing library for ML interpretability. I decided to build a simple xgboost classifier using a toy dataset from sklearn and to draw a force_plot.
To understand the plot the library says:
The above explanation shows features each contributing to push the
model output from the base value (the average model output over the
training dataset we passed) to the model output. Features pushing the
prediction higher are shown in red, those pushing the prediction lower
are in blue (these force plots are introduced in our Nature BME
paper).
So it looks to me as the base_value should be the same as clf.predict(X_train).mean()which equals 0.637. However this is not the case when looking at the plot, the number is actually not even within [0,1]. I tried doing the log in different basis (10, e, 2) assuming it would be some kind of monotonic transformation... but still not luck. How can I get to this base_value?
!pip install shap
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.ensemble import GradientBoostingClassifier
import pandas as pd
import shap
X, y = load_breast_cancer(return_X_y=True)
X = pd.DataFrame(data=X)
y = pd.DataFrame(data=y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
clf = GradientBoostingClassifier(random_state=0)
clf.fit(X_train, y_train)
print(clf.predict(X_train).mean())
# load JS visualization code to notebook
shap.initjs()
explainer = shap.TreeExplainer(clf)
shap_values = explainer.shap_values(X_train)
# visualize the first prediction's explanation (use matplotlib=True to avoid Javascript)
shap.force_plot(explainer.expected_value, shap_values[0,:], X_train.iloc[0,:])
To get base_value in raw space (when link="identity") you need to unwind class labels --> to probabilities --> to raw scores. Note, the default loss is "deviance", so the raw is inverse sigmoid:
# probabilites
y = clf.predict_proba(X_train)[:,1]
# raw scores, default link="identity"
y_raw = np.log(y/(1-y))
# expected raw score
print(np.mean(y_raw))
print(np.isclose(explainer.expected_value, np.mean(y_raw), 1e-12))
2.065861773054686
[ True]
The relevant plot for 0th data point in raw space:
shap.force_plot(explainer.expected_value[0], shap_values[0,:], X_train.iloc[0,:], link="identity")
Should you wish to switch to sigmoid probability space (link="logit"):
from scipy.special import expit, logit
# probabilites
y = clf.predict_proba(X_train)[:,1]
# exected raw base value
y_raw = logit(y).mean()
# expected probability, i.e. base value in probability spacy
print(expit(y_raw))
0.8875405774316522
The relevant plot for 0th data point in probability space:
Note, the probability base_value from shap's perspective, what they call a baseline probability if no data is available, is not what a reasonable person would define by having no independent variables (0.6373626373626373 in this case)
Full reproducible example:
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.ensemble import GradientBoostingClassifier
import pandas as pd
import shap
print(shap.__version__)
X, y = load_breast_cancer(return_X_y=True)
X = pd.DataFrame(data=X)
y = pd.DataFrame(data=y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
clf = GradientBoostingClassifier(random_state=0)
clf.fit(X_train, y_train.values.ravel())
# load JS visualization code to notebook
shap.initjs()
explainer = shap.TreeExplainer(clf, model_output="raw")
shap_values = explainer.shap_values(X_train)
from scipy.special import expit, logit
# probabilites
y = clf.predict_proba(X_train)[:,1]
# exected raw base value
y_raw = logit(y).mean()
# expected probability, i.e. base value in probability spacy
print("Expected raw score (before sigmoid):", y_raw)
print("Expected probability:", expit(y_raw))
# visualize the first prediction's explanation (use matplotlib=True to avoid Javascript)
shap.force_plot(explainer.expected_value[0], shap_values[0,:], X_train.iloc[0,:], link="logit")
Output:
0.36.0
Expected raw score (before sigmoid): 2.065861773054686
Expected probability: 0.8875405774316522
I recently discovered this amazing library for ML interpretability. I decided to build a simple xgboost classifier using a toy dataset from sklearn and to draw a force_plot.
To understand the plot the library says:
The above explanation shows features each contributing to push the
model output from the base value (the average model output over the
training dataset we passed) to the model output. Features pushing the
prediction higher are shown in red, those pushing the prediction lower
are in blue (these force plots are introduced in our Nature BME
paper).
So it looks to me as the base_value should be the same as clf.predict(X_train).mean()which equals 0.637. However this is not the case when looking at the plot, the number is actually not even within [0,1]. I tried doing the log in different basis (10, e, 2) assuming it would be some kind of monotonic transformation... but still not luck. How can I get to this base_value?
!pip install shap
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.ensemble import GradientBoostingClassifier
import pandas as pd
import shap
X, y = load_breast_cancer(return_X_y=True)
X = pd.DataFrame(data=X)
y = pd.DataFrame(data=y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
clf = GradientBoostingClassifier(random_state=0)
clf.fit(X_train, y_train)
print(clf.predict(X_train).mean())
# load JS visualization code to notebook
shap.initjs()
explainer = shap.TreeExplainer(clf)
shap_values = explainer.shap_values(X_train)
# visualize the first prediction's explanation (use matplotlib=True to avoid Javascript)
shap.force_plot(explainer.expected_value, shap_values[0,:], X_train.iloc[0,:])
To get base_value in raw space (when link="identity") you need to unwind class labels --> to probabilities --> to raw scores. Note, the default loss is "deviance", so the raw is inverse sigmoid:
# probabilites
y = clf.predict_proba(X_train)[:,1]
# raw scores, default link="identity"
y_raw = np.log(y/(1-y))
# expected raw score
print(np.mean(y_raw))
print(np.isclose(explainer.expected_value, np.mean(y_raw), 1e-12))
2.065861773054686
[ True]
The relevant plot for 0th data point in raw space:
shap.force_plot(explainer.expected_value[0], shap_values[0,:], X_train.iloc[0,:], link="identity")
Should you wish to switch to sigmoid probability space (link="logit"):
from scipy.special import expit, logit
# probabilites
y = clf.predict_proba(X_train)[:,1]
# exected raw base value
y_raw = logit(y).mean()
# expected probability, i.e. base value in probability spacy
print(expit(y_raw))
0.8875405774316522
The relevant plot for 0th data point in probability space:
Note, the probability base_value from shap's perspective, what they call a baseline probability if no data is available, is not what a reasonable person would define by having no independent variables (0.6373626373626373 in this case)
Full reproducible example:
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.ensemble import GradientBoostingClassifier
import pandas as pd
import shap
print(shap.__version__)
X, y = load_breast_cancer(return_X_y=True)
X = pd.DataFrame(data=X)
y = pd.DataFrame(data=y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
clf = GradientBoostingClassifier(random_state=0)
clf.fit(X_train, y_train.values.ravel())
# load JS visualization code to notebook
shap.initjs()
explainer = shap.TreeExplainer(clf, model_output="raw")
shap_values = explainer.shap_values(X_train)
from scipy.special import expit, logit
# probabilites
y = clf.predict_proba(X_train)[:,1]
# exected raw base value
y_raw = logit(y).mean()
# expected probability, i.e. base value in probability spacy
print("Expected raw score (before sigmoid):", y_raw)
print("Expected probability:", expit(y_raw))
# visualize the first prediction's explanation (use matplotlib=True to avoid Javascript)
shap.force_plot(explainer.expected_value[0], shap_values[0,:], X_train.iloc[0,:], link="logit")
Output:
0.36.0
Expected raw score (before sigmoid): 2.065861773054686
Expected probability: 0.8875405774316522
I have been playing around with lasso regression on polynomial functions using the code below. The question I have is should I be doing feature scaling as part of the lasso regression (when attempting to fit a polynomial function). The R^2 results and plot as outlined in the code I have pasted below suggests not. Appreciate any advice on why this is not the case or if I have fundamentally stuffed something up. Thanks in advance for any advice.
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
np.random.seed(0)
n = 15
x = np.linspace(0,10,n) + np.random.randn(n)/5
y = np.sin(x)+x/6 + np.random.randn(n)/10
X_train, X_test, y_train, y_test = train_test_split(x, y, random_state=0)
def answer_regression():
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import Lasso, LinearRegression
from sklearn.metrics.regression import r2_score
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
scaler = MinMaxScaler()
global X_train, X_test, y_train, y_test
degrees = 12
poly = PolynomialFeatures(degree=degrees)
X_train_poly = poly.fit_transform(X_train.reshape(-1,1))
X_test_poly = poly.fit_transform(X_test.reshape(-1,1))
#Lasso Regression Model
X_train_scaled = scaler.fit_transform(X_train_poly)
X_test_scaled = scaler.transform(X_test_poly)
#No feature scaling
linlasso = Lasso(alpha=0.01, max_iter = 10000).fit(X_train_poly, y_train)
y_test_lassopredict = linlasso.predict(X_test_poly)
Lasso_R2_test_score = r2_score(y_test, y_test_lassopredict)
#With feature scaling
linlasso = Lasso(alpha=0.01, max_iter = 10000).fit(X_train_scaled, y_train)
y_test_lassopredict_scaled = linlasso.predict(X_test_scaled)
Lasso_R2_test_score_scaled = r2_score(y_test, y_test_lassopredict_scaled)
%matplotlib notebook
plt.figure()
plt.scatter(X_test, y_test, label='Test data')
plt.scatter(X_test, y_test_lassopredict, label='Predict data - No Scaling')
plt.scatter(X_test, y_test_lassopredict_scaled, label='Predict data - With Scaling')
return (Lasso_R2_test_score, Lasso_R2_test_score_scaled)
answer_regression()```
Your X range is around [0,10], so the polynomial features will have a much wider range. Without scaling, their weights are already small (because of their larger values), so Lasso will not need to set them to zero. If you scale them, their weights will be much larger, and Lasso will set most of them to zero. That's why it has a poor prediction for the scaled case (those features are needed to capture the true trend of y).
You can confirm this by getting the weights (linlasso.coef_) for both cases, where you will see that most of the weights for the second case (scaled one) are set to zero.
It seems your alpha is larger than an optimal value and should be tuned. If you decrease alpha, you will get similar results for both cases.
This is the code I built to apply a multiple linear regression. I added standard scaler to fix the Y intercept p-value which was not significant but the problem that the results of CV RMSE in the end changed and have nosense anymore and received an error in the code for plotting the correlation Matrix saying : AttributeError: 'numpy.ndarray' object has no attribute 'corr'
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import statsmodels.api as sm
from scipy import stats
from scipy.stats.stats import pearsonr
# Import Excel File
data = pd.read_excel("C:\\Users\\AchourAh\\Desktop\\Multiple_Linear_Regression\\SP Level Reasons Excels\\SP000273701_PL14_IPC_03_09_2018_Reasons.xlsx",'Sheet1') #Import Excel file
# Replace null values of the whole dataset with 0
data1 = data.fillna(0)
print(data1)
# Extraction of the independent and dependent variables
X = data1.iloc[0:len(data1),[1,2,3,4,5,6,7]] #Extract the column of the COPCOR SP we are going to check its impact
Y = data1.iloc[0:len(data1),9] #Extract the column of the PAUS SP
# Data Splitting to train and test set
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size =0.25,random_state=1)
from sklearn.preprocessing import StandardScaler
ss = StandardScaler()
X_train = ss.fit_transform(X_train)
X_test = ss.transform(X_test)
# Statistical Analysis of the training set with Statsmodels
X = sm.add_constant(X_train) # add a constant to the model
est = sm.OLS(Y_train, X).fit()
print(est.summary()) # print the results
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
import math
lm = LinearRegression() # create an lm object of LinearRegression Class
lm.fit(X_train,Y_train) # train our LinearRegression model using the training set of data - dependent and independent variables as parameters. Teaching lm that Y_train values are all corresponding to X_train.
print(lm.intercept_)
print(lm.coef_)
mse_test = mean_squared_error(Y_test, lm.predict(X_test))
print(math.sqrt(mse_test))
# Data Splitting to train and test set of the reduced data
X_1 = data1.iloc[0:len(data1),[1,2]] #Extract the column of the COPCOR SP we are going to check its impact
X_train2, X_test2, Y_train2, Y_test2 = train_test_split(X_1, Y, test_size =0.25,random_state=1)
X_train2 = ss.fit_transform(X_train2)
X_test2 = ss.transform(X_test2)
# Statistical Analysis of the reduced model with Statsmodels
X_reduced = sm.add_constant(X_train2) # add a constant to the model
est_reduced = sm.OLS(Y_train2, X_reduced).fit()
print(est_reduced.summary()) # print the results
# Fitting a Linear Model for the reduced model with Scikit-Learn
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
import math
lm1 = LinearRegression() #create an lm object of LinearRegression Class
lm1.fit(X_train2, Y_train2)
print(lm1.intercept_)
print(lm1.coef_)
mse_test1 = mean_squared_error(Y_test2, lm1.predict(X_test2))
print(math.sqrt(mse_test1))
#Cross Validation and Training again the model
from sklearn.model_selection import KFold
from sklearn import model_selection
kf = KFold(n_splits=6, random_state=1)
for train_index, test_index in kf.split(X_train2):
print("Train:", train_index, "Validation:",test_index)
X_train1, X_test1 = X[train_index], X[test_index]
Y_train1, Y_test1 = Y[train_index], Y[test_index]
results = -1 * model_selection.cross_val_score(lm1, X_train1, Y_train1,scoring='neg_mean_squared_error', cv=kf)
print(np.sqrt(results))
#RMSE values interpretation
print(math.sqrt(mse_test1))
print(math.sqrt(results.mean()))
#Good model built no overfitting or underfitting (Barely Same for test and training :Goal of Cross validation but low prediction accuracy = Value is big
import seaborn
Corr=X_train2.corr(method='pearson')
mask=np.zeros_like(Corr)
mask[np.triu_indices_from(mask)]=True
seaborn.heatmap(Corr,cmap='RdYlGn_r',vmax=1.0,vmin=-1.0,mask=mask, linewidths=2.5)
plt.yticks(rotation=0)
plt.xticks(rotation=90)
plt.show()
enter code here
Do you have an idea how to fix the issue ?
I'm guessing the problem lies with:
Corr=X_train2.corr(method='pearson')
.corr is a pandas dataframe method but X_train2 is a numpy array at that stage. If a dataframe/series is passed into StandardScaler, a numpy array is returned. Try replacing the above with:
Corr=pd.DataFrame(X_train2).corr(method='pearson')
or make use of numpy.corrcoef or numpy.correlate in their respective forms.