Initialization function for HiddenMarkovModel Attributes: observable_states (list): A list containing the name of each observable

lamda : L1_penality

>>> data = [[-1, 2], [-0.5, 6], [0, 10], [1, 18]] >>> scaler = MinMaxScaler() >>> print(scaler.fit(data)) MinMaxScale

>>> scaler = StandardScaler() >>> data = [[0, 0], [0, 0], [1, 1], [1, 1]] >>> print(scaler.fit(data)) StandardScaler(

Initialization of Clusters for K Means.

Custom Implementation of K Means.

Lowess regression (Locally weighted regression) Arguments - window (by default 10) degree(by default 1)

Linear regression Arguments - alpha (by default .001) epochs(by default 100) plot : bool - pl

X.shape = (m,n) Y.shape = (m,) where, m = number of training examples n = number of features

first finding the size of given features. m=no. of given training sets n=no.features in each training set after tha

Input parameters: X --> array, features y --> array, true values Returns: None

Some pre-defined checks 1) length of x and y array should be same 2) Window size cannot exceed the number of data points

X: training features y: target variable The function returns: A dictionary with the probability, mean, and standard deviat

y_test: actual values y_pred: predicted values The function returns: A number between 0-1, representing the percentage of

X: test dataset The function returns: List of predicted class for each row of dataset.

Input parameters: X --> array, features Returns: array, predictions

Prints the result of the Backward Algorithm. Args: beta (np.array): A matrix of the beta values. b_prob (numpy.float64): The comp

Prints the result of the Forward Algorithm. Args: alpha (np.array): A matrix of the alpha values. a_prob (numpy.float64): The com

Prints the result of the Viterbi Algorithm. Args: input_seq (list): A list of the observed input sequence. observable_states (lis