Home Points Spread (-1.5) basketball predictions tomorrow (2025-11-04)

Pronostici Finali per Domani

Pronostico per il Match Squadra A vs Squadra C

Data l'analisi dettaglia<|repo_name|>kalyanaraman/voice-identifier<|file_sep|>/README.md # voice-identifier Using machine learning to identify the speaker from the audio sample ## Data The data is from [Kaggle](https://www.kaggle.com/primaryobjects/voicegender) ## Training The training is done using the MFCC features and the Linear SVC model. python train.py ## Testing The testing is done by providing the path to the audio file. python test.py ../data/test.wav <|file_sep|># import modules import os import sys import numpy as np from sklearn.model_selection import train_test_split from sklearn.metrics import accuracy_score from sklearn.svm import SVC import matplotlib.pyplot as plt from python_speech_features import mfcc # define path to the dataset folder path = "../data" files = os.listdir(path) # initialize lists to store the data and labels mfccs = [] labels = [] # loop through each file and extract features and labels for file_name in files: # load the audio file and extract features and labels file_path = os.path.join(path,file_name) label = file_name.split("-")[0] if label == "female": label = "FEMALE" else: label = "MALE" signal,sample_rate = librosa.load(file_path) mfcc_feature = mfcc(signal,sample_rate) # append feature and label to lists mfccs.append(mfcc_feature) labels.append(label) # convert lists to numpy arrays mfccs = np.asarray(mfccs) labels = np.asarray(labels) # split the data into train and test sets (80/20 split) X_train,X_test,y_train,y_test = train_test_split(mfccs, labels, test_size=0.2, random_state=42) # train a linear SVC model on the training set clf = SVC(kernel='linear',probability=True) clf.fit(X_train,y_train) # evaluate the model on the test set using accuracy score metric y_pred = clf.predict(X_test) acc_score = accuracy_score(y_test,y_pred) # plot confusion matrix cm = confusion_matrix(y_test,y_pred) plt.imshow(cm,cmap='Blues',interpolation='nearest') plt.colorbar() plt.xticks(np.arange(2),['FEMALE','MALE']) plt.yticks(np.arange(2),['FEMALE','MALE']) plt.xlabel('Predicted') plt.ylabel('Actual') plt.title('Confusion Matrix') plt.show() print("Accuracy Score:",acc_score) <|repo_name|>kalyanaraman/voice-identifier<|file_sep|>/train.py # import modules import os import sys import librosa import numpy as np from sklearn.model_selection import train_test_split from sklearn.metrics import accuracy_score from sklearn.svm import SVC import matplotlib.pyplot as plt from python_speech_features import mfcc # define path to the dataset folder path = "../data" files = os.listdir(path) # initialize lists to store the data and labels mfccs = [] labels = [] # loop through each file and extract features and labels for file_name in files: # load the audio file and extract features and labels file_path = os.path.join(path,file_name) label = file_name.split("-")[0] if label == "female": label = "FEMALE" else: label = "MALE" signal,sample_rate = librosa.load(file_path) mfcc_feature = mfcc(signal,sample_rate) # append feature and label to lists mfccs.append(mfcc_feature) labels.append(label) # convert lists to numpy arrays mfccs = np.asarray(mfccs) labels = np.asarray(labels) print("Total Number of Samples: ",len(mfccs)) print("Number of Female Samples: ",np.sum(labels == 'FEMALE')) print("Number of Male Samples: ",np.sum(labels == 'MALE')) # split the data into train and test sets (80/20 split) X_train,X_test,y_train,y_test = train_test_split(mfccs, labels, test_size=0.2, random_state=42) print("Train Set Shape: ",X_train.shape) print("Test Set Shape: ",X_test.shape) # train a linear SVC model on the training set clf = SVC(kernel='linear',probability=True) clf.fit(X_train,y_train) # evaluate the model on the test set using accuracy score metric y_pred = clf.predict(X_test) acc_score = accuracy_score(y_test,y_pred) print("Accuracy Score:",acc_score) filename="trained_model.pkl" pickle.dump(clf,filename)<|file_sep|># import modules import pickle import numpy as np from python_speech_features import mfcc def predict(path): # load the trained model from disk filename="trained_model.pkl" clf=pickle.load(open(filename,'rb')) # load audio file and extract MFCC features signal,sample_rate=librosa.load(path) mfcc_feature=mfcc(signal,sample_rate) # predict using trained model y_pred=clf.predict([mfcc_feature]) return y_pred[0] if __name__=="__main__": path=sys.argv[1] print(predict(path)) <|repo_name|>DrDukeKhan/cryptopals<|file_sep|>/set1/challenge6.py #!/usr/bin/env python3 """ Solve challenge #6 from cryptopals.com set #1. """ import binascii def xor_strings(s1: bytes, s2: bytes) -> bytes: """ XOR two strings together. :param s1: The first string. :param s2: The second string. :return: The XORed string. """ return bytes([x ^ y for x, y in zip(s1, s2)]) def single_byte_xor(s: bytes) -> bytes: """ XOR a string against all possible single-byte keys and return each result with its corresponding key. :param s: The string. :return: List of tuples containing (resulting string, corresponding key). """ return [(xor_strings(s, b'x00' * len(s) + b'x%02x' % key), key) for key in range(256)] def hamming_distance(s1: bytes, s2: bytes) -> int: """ Compute Hamming distance between two byte strings. :param s1: The first byte string. :param s2: The second byte string. :return: Hamming distance between `s1` and `s2`. """ return sum(bin(x ^ y).count('1') for x, y in zip(s1, s2)) def normalized_hamming_distance(s: bytes) -> float: """ Compute normalized Hamming distance of `s` with itself offset by one byte. :param s: The byte string. :return: Normalized Hamming distance between `s` and `s` offset by one byte. """ return hamming_distance(s[:len(s)-1], s[1:]) / (len(s) - 1) def break_single_byte_xor(cipher_text): # First we will compute normalized Hamming distances between blocks of size # `block_size` within our cipher text. block_size = len(cipher_text) // 16 distances_by_block_pair_and_key_by_block_pair_and_key_ = {} for index_a in range(0,len(cipher_text)-block_size*2+1,