Related
I am trying to run a RandomizedSearchCV on various classification models through "For" loop for Hyperparameter tuning. There is no issue with running any other models except CatBoost. Also the issue with Catboost arises when I used Pipeline in defining function.
My Code:
#Building the models:
lr = LogisticRegression()
knn = KNeighborsClassifier()
svm = SVC()
dt = DecisionTreeClassifier(random_state=1)
bag = BaggingClassifier(random_state=1)
adb = AdaBoostClassifier(random_state=1)
gb = GradientBoostingClassifier(random_state=1)
rf = RandomForestClassifier(random_state=1)
xgb = XGBClassifier()
cgb = CatBoostClassifier()
lgb = LGBMClassifier()
#Defining a function:
def fun_exp(model, name, x_tr, x_te, y_tr, y_te):
start = time.time()
pipe = Pipeline([('scale', StandardScaler()), ('pca', PCA(n_components = 62)), (name, model)])
rscv = RandomizedSearchCV(pipe, params, cv=10, random_state=1)
rscv.fit(x_tr, y_tr)
rscv_best_params = rscv.best_params_
rscv_best_score = rscv.best_score_
rscv_score_train = rscv.score(x_tr, y_tr)
rscv_score_test = rscv.score(x_te, y_te)
rscv_pred = rscv.predict(x_te)
end = time.time()
pickle.dump(rscv, open(name, 'wb'))
rscv_duration = end-start
return rscv_best_params, rscv_best_score, rscv_score_train, rscv_score_test, rscv_duration, rscv_pred
Running the above function in for loop & saving the result in a dictionary:
exp_result = {}
\#Fitting & Testing the model
for model, name in zip([lr, knn, svm, dt, bag, adb, gb, rf, lgb, cgb, xgb], ['Logistic Regression', 'KNeighbors', 'SVM', 'DecisionTree', 'Bagging', 'AdaBoost', 'GradientBoost', 'Random Forest', 'LightGBM', 'CatBoost', 'XGBoost']):
if model == lr:
params = {'Logistic Regression__solver': ['liblinear', 'lfbgs', 'sag', 'saga'], 'Logistic Regression__penalty':['elasticnet', 'l1', 'l2', 'none'], 'Logistic Regression__multi_class': ['auto', 'ovr', 'multinomial'], 'Logistic Regression__C':[0.1, 1, 10], 'Logistic Regression__tol': [0.00001, 0.0001, 0.001], 'Logistic Regression__class_weight': ['balanced', None]}
if model == knn:
params = {'KNeighbors__n_neighbors':np.arange(5,50,5), 'KNeighbors__weights': ['uniform', 'distance'], 'KNeighbors__algorithm':['auto', 'knn__ball_tree', 'kd_tree', 'brute'], 'KNeighbors__leaf_size': np.arange(10,51,10), 'KNeighbors__metric': ['minkowski', 'euclidean', 'manhattan']}
if model == svm:
params = {'SVM__gamma': [10, 1, 0.1, 0.01, 0.001, 0.0001], 'SVM__C': [1000, 100, 10, 1, 0.1, 0.01, 0.001], 'SVM__kernel': ['poly', 'rbf', 'sigmoid'], 'SVM__class_weight': ['balanced', None], 'SVM__decision_function_shape': ['ovo', 'ovr']}
if model == dt:
params = {'DecisionTree__criterion':['gini', 'entropy', 'log_loss'], 'DecisionTree__splitter':['best', 'random'], 'DecisionTree__max_depth':[None, np.arange(1,11)], 'DecisionTree__max_features': np.arange(8, 21, 2), 'DecisionTree__random_state':[1], 'DecisionTree__class_weight':['balanced', None]}
if model==bag:
params = {'Bagging__n_estimators': [10, 30, 50, 100, 500], 'Bagging__max_features': np.arange(8, 21, 2), 'Bagging__random_state':[1]}
if model == adb:
params = {'AdaBoost__n_estimators': [10, 30, 50, 100, 500], 'AdaBoost__learning_rate':[0.001, 0.01, 0.1, 1, 10], 'AdaBoost__algorithm':['SAMME.R', 'SAMME'], 'AdaBoost__random_state':[1]}
if model == gb:
params = {'GradientBoost__loss':['log_loss', 'exponential'], 'GradientBoost__learning_rate':[0.001, 0.01, 0.1, 1, 10], 'GradientBoost__n_estimators': [10, 30, 50, 100, 500], 'GradientBoost__max_depth':np.arange(1,11), 'GradientBoost__random_state':[1], 'GradientBoost__max_features': np.arange(8, 21, 2)}
if model == rf:
params = {'Random Forest__n_estimators': [10, 30, 50, 100, 500], 'Random Forest__criterion':['gini', 'entropy', 'log_loss'], 'Random Forest__max_depth':np.arange(1,11), 'Random Forest__max_features': np.arange(8, 21, 2), 'Random Forest__random_state':[1]}
if model == lgb:
params = {'LightGBM__boosting_type':['gbdt', 'rf'], 'LightGBM__num_leaves':np.arange(20, 40), 'LightGBM__max_depth':np.arange(1,11), 'LightGBM__learning_rate':[0.001, 0.01, 0.1, 1, 10], 'LightGBM__n_estimators': [10, 30, 50, 100, 500], 'LightGBM__class_weight': ['balanced', None], 'LightGBM__random_state':[1]}
if model == cgb:
params = {'CatBoost__learning_rate':[0.001, 0.01, 0.1, 1], 'CatBoost__n_estimators': [100, 500], 'CatBoost__max_depth':np.arange(1,11), 'CatBoost__random_state':[1], 'CatBoost__feature_border_type': ['Median', 'Uniform', 'UniformAndQuantiles', 'GreedyLogSum', 'MaxLogSum', 'MinEntropy']}
if model == xgb:
le = LabelEncoder()
y_tr = le.fit_transform(y_tr)
y_te = le.fit_transform(y_te)
params = {'XGBoost__n_estimators': [10, 30, 50, 100, 500], 'XGBoost__max_depth':np.arange(1,11), 'XGBoost__max_leaves': np.arange(0, 150), 'XGBoost__learning_rate':[0.001, 0.01, 0.1, 1, 10], 'XGBoost__random_state':[1]}
exp_result[name] = fun_exp(model, name, x_tr, x_te, y_tr, y_te)
I'm attempting to have an X-Axis with dates. Unfortunately my data can be have a small range resulting in a date showing multiple times as an xTick. Is there a way to force it to only show "each date" exactly once as a tick.
For example, I don't want to see 12/29/2020 as a tick more than once.
Depends on your version of d3, but d3.timeDay might be what you need.
var input = [new Date(1999, 11, 31, 0),new Date(2000, 0, 1, 0), new Date(2000, 0, 1, 2), new Date(2000, 0, 1, 3), new Date(2000, 0, 2, 2), new Date(2000, 0, 2, 5)];
console.log(input);
var x = d3.scaleTime().domain(input);
var xTick = x.ticks(d3.timeDay.every(1));
console.log(xTick)
<script src="https://cdnjs.cloudflare.com/ajax/libs/d3/5.7.0/d3.min.js"></script>
I'm mystified. In this code:
SynthDef(\acid,
{
|out, gate = 1, freq, myParam, amp, cutoff, resonance, filtEnvAmt|
var env, audio, filtEnv;
if (myParam == \something, { freq = 200; });
env = Linen.kr(gate, 0, 1, 0, doneAction: 2);
audio = LFSaw.ar(freq, mul: amp);
filtEnv = Line.kr(midicps(cutoff + filtEnvAmt), midicps(cutoff), 0.2);
audio = RLPFD.ar(audio, ffreq: filtEnv + MouseX.kr(0, 5000), res: MouseY.kr(0, 1), dist: 0);
Out.ar(out, audio * env);
}
).add;
b = Pbind(*[
out: 0,
instrument: \acid,
stepsPerOctave: 19,
scale: [0, 3, 5, 8, 11, 14, 17],
octave: 3,
degree: Pseq([0, \, 3, 3, 4, 4, 9, 4, 4]),
myParam: \something,
//prevFreq: Pseq([0, 0, 0, 0, 9, 0, 0, 0, 0]),
dur: Pseq([0.4, 0.4, 0.1, 0.1, 0.1, 0.1, 0.2, 0.1, 0.1]),
cutoff: Pseq([60, \, 50, 60, 80, 60, 90, 80, 50]),
filtEnvAmt: Pseq([20, \, 20, 20, 20, 20, -10, 20, 20]),
resonance: Pseq([0.5, \, 0.5, 0.5, 0.5, 0.5, 0.3, 0.5, 0.5])
]);
b.play;
..the equality test myParam == \something never returns true, despite the fact that the Pbind is clearly sending \something each time. No other value will work either: 0, nil etc.
The equality tests myParam == myParam and \something == \something do work however, so in these cases I get a monotone melody.
I can only guess that a Pbind sends each value in some kind of wrapper, but I've no idea how to then check them from inside the synth. Can anyone help?
First: you can't send symbols to a synth control. You can only send numbers.
Second: your example doesn't say what freq should be if the test is false. In fact, you should write it in more of a dataflow style such as:
freq = if(testcondition, 200, 300);
That's the kind of thing that will work in a synthdef.
Third is a slightly frustrating thing in sc language, which is that the == message is always evaluated at synthdef compile time - the equality is checked once, and then never again. In order to have "live" equality checking, you can use this slightly clunky expression:
BinaryOpUGen("==", thinga, thingb)
So in summary you might write
freq = if(BinaryOpUGen("==", myParam, 1), 200, 300);
I'm not sure whether SuperCollider can deliver moons on sticks, but I'd really like to be able to specify values in my Pbind that are interpreted in the same way as midinote or degree: i.e. converted automatically to a frequency.
So, an excerpt of such a Pbind, which produces a TB-303-style slide from one frequency to another:
b = Pbind(*[
out: 0,
instrument: \acid,
stepsPerOctave: 19,
scale: [0, 3, 5, 8, 11, 14, 17],
octave: 3,
degree: Pseq([0, \, 3, 3, 4, 4, 9, 4, 4]),
prevFreq: Pseq([\, \, 0, 3, 3, 4, 4, 9, 4]),
dur: Pseq([0.4, 0.4, 0.1, 0.1, 0.1, 0.1, 0.2, 0.1, 0.1]),
]);
...it would be super-duper if prevFreq were interpreted as containing degree values in the same way as degree.
In the absence of some kind of automatic conversion, I assume I need to do some kind of calculation within the synth itself in order to convert my values from a degree-type value to an actual frequency. I'm aware I can use foo.midicps to convert midinote-type values to a frequency, but is there a similar convenience function to convert degree-type values to a frequency (presumably also using the current scale and octave values)?
If you look at the helpfile for Event, you can see how it computes the frequency from the degree and scale:
note: #{ // note is the note in halftone steps from the root
(~degree + ~mtranspose).degreeToKey(~scale, ~stepsPerOctave);
}
midinote: #{ // midinote is the midinote (continuous intermediate values)
((~note.value + ~gtranspose + ~root) / ~stepsPerOctave + ~octave) * 12.0;
}
freq: #{
(~midinote.value + ~ctranspose).midicps * ~harmonic;
}
detunedFreq: #{ // finally sent as "freq" to the synth as a parameter, if given
~freq.value + ~detune
}
Event is an associative array and those ~variables can also be used as keys to the array (something which will hopefully become clear in a moment. It's also possible to get access to the events in a Pbind, by using a Pfunc. Let's say we want to calculate the current frequency for your Pbind:
b = Pbind(*[
out: 0,
instrument: \default,
stepsPerOctave: 19,
scale: [0, 3, 5, 8, 11, 14, 17],
octave: 3,
degree: Pseq([0, \, 3, 3, 4, 4, 9, 4, 4]),
dur: Pseq([0.4, 0.4, 0.1, 0.1, 0.1, 0.1, 0.2, 0.1, 0.1]),
foo: Pfunc({|evt|
var note, midinote, freq, detuned, result;
note = (evt[\degree] + evt[\mtranspose]).degreeToKey(evt[\scale], evt[\stepsPerOctave]);
midinote = ((note + evt[\gtranspose] + evt[\root]) / evt[\stepsPerOctave] + evt[\octave]) * 12.0;
freq = (midinote + evt[\ctranspose]).midicps * evt[\harmonic];
detuned = freq + evt[\detune];
detuned.postln;
})
]).play
Those calculations for note, midinote, freq and detuned freq are the same calculations we saw in the event helpfile. Therefore, this Pbind will now print out the frequency that you are currently playing.
What you actually want is the frequency you were previously playing, which we could figure out from your array of previous degrees. Or we could just keep track of the previous frequency in a variable. This will be a lot easier to keep track of!
(
var prev;
b = Pbind(*[
out: 0,
instrument: \default,
stepsPerOctave: 19,
scale: [0, 3, 5, 8, 11, 14, 17],
octave: 3,
degree: Pseq([0, \rest, 3, 3, 4, 4, 9, 4, 4]),
dur: Pseq([0.4, 0.4, 0.1, 0.1, 0.1, 0.1, 0.2, 0.1, 0.1]),
prevFreq: Pfunc({|evt|
var note, midinote, freq, detuned, result;
if (evt[\degree] == \rest, { detuned = \rest} , {
note = (evt[\degree] + evt[\mtranspose]).degreeToKey(evt[\scale], evt[\stepsPerOctave]);
midinote = ((note + evt[\gtranspose] + evt[\root]) / evt[\stepsPerOctave] + evt[\octave]) * 12.0;
freq = (midinote + evt[\ctranspose]).midicps * evt[\harmonic];
detuned = freq + evt[\detune];
});
//detuned.postln;
if (prev.isNil(), {
result = \rest;
} ,
{
result = prev;
});
prev = detuned
})
]).play
)
How do I ensure that bars in multibarchart in nvd3 always starts from same level? What I am seeing is that some series start kinda "floating" in the air (actually one of the stacks loses its color)
Please see http://jsfiddle.net/TZ2kH/1/ and click on "stacked" option (initial settings - that is another question)
My data series is very short, just 3 rows - 2 in one sub-series and 1 in another sub-series.
data_multiBarChart = [{
'values': [ {
'y': 7,
'x': 9
}],
'key': 'Count',
'yAxis': '1'
}, {
'values': [{
'y': 12,
'x': 0
}, {
'y': 8,
'x': 1
}],
'key': 'Duration',
'yAxis': '1'
}];
Thanks.
--EDIT--
FWIW warnings seen in firebug console:
Unexpected value NaN parsing height attribute.
this.setAttribute(name, f(t));
I have also seen with similarly sparse data:
Unexpected value NaN parsing height attribute.
...3.interpolateRgb=function(e,t){e=d3.rgb(e),t=d3.rgb(t);var n=e.r,r=e.g,i=e.b,s=t...
Its because of the data you are passing into the chart. The count of sub-series in you chart must be equal, if you do not have a value you must at least set the y value to 0.
A multiple bar graph contains comparisons of two or more categories or bars. When the chart is drawn, the X-Axis must be in a sequence, take a look at how the X-Axis is lined up in this fiddle
Try using the data as shown below :
data_multiBarChart = [{
'values': [{
'y': 0,
'x': 1
}, {
'y': 8,
'x': 2
}],
'key': 'Count',
'yAxis': '1'
}, {
'values': [{
'y': 12,
'x': 1
}, {
'y': 8,
'x': 2
}],
'key': 'Duration',
'yAxis': '1'
}];
Hope I made sense, and helps solve your problem.