Python for Data Analysis

📙 Model accuracy assessment, retraining, regularization (XGBClassifier, roc_curve, precision_recall_curve)
📗 Shelter Animal Outcomes (Kaggle competition)
📙 Polynomial Regression and Proximity Metrics (Levenshtein distance)
📙 Polynomial Regression and Proximity Metrics (kNN digits)
📙 Clustering Algorithms (KMeans, DBSCAN, adjusted_rand_score, silhouette_score)
📙 Wine quality assessment (Analysis, LinearRegression, RandomForestRegressor)
📙 Iris Dataset (RandomForest, LogisticRegression)
📙 Adult Dataset (SVM, LogisticRegression)
📗 KNeighborsClassifier
📗 Titanic Dataset
📙 Titanic Dataset (DecisionTreeClassifier, GridSearchCV)
📗 Clustering inclass
📗 Ensemble (models)
📙 Ensemble (StackingCVRegressor, GradientBoostingRegressor, BaggingRegressor, AdaBoostRegressor)
📗 Moons circles (KMeans, AgglomerativeClustering, DBSCAN, AffinityPropagation)
📗 Loss Functions and Optimization (theory)
📗 Athletes classifier (Model accuracy assessment, retraining, regularization)
📙 Loss Functions and Optimization (gradient descent, nesterov momentum, rmsprop)
📗 Improved model quality. Advanced classification algorithms (test)
📙 Improved model quality, Advanced algorithms (GridSearchCV, best_params, best_score, best_estimator)
📗 Collaborative filtering (part 1, package Surprise)
📙 Machine Learning Laboratory work on modeling

📙 Introduction and classification of recommendation systems
📗 Content Based Recommendations (TfidfTransformer, CountVectorizer, TfidfVectorizer)
📙 Content Based Recommendations (preprocessing, StackingCVRegressor)
📙 Collaborative filtering (part 2, package Surprise, KNNBasic, KNNWithMeans, SVD, SVDpp, accuracy)
📗 Recommendations based on hidden factors (implicit, sparse)
📙 Hybrid Recommender Systems
📗 Hybrid Recommender Systems (surprise, NearestNeighbors)
📗 Hybrid Recommender Systems (lightfm)

📗 Introducing Time Series (candlestick_ohlc, mpl_finance, visualization)
📗 TS Practice (adfuller, boxcox)
📗 Basic Full Analysis Example (adfuller, sm, smt, boxcox)
📙 Elementary time series analysis methods (MA, WMA, EMA, DEMA, TEMA)
📙 ARIMA and GARCH models, predicting values based on them (ARMA, ARIMA, ARCH, GARCH)
📗 Markovsky random processes (construction of Markov models for time series, predicting values)
📗 Time series debugging and anomaly detection
📙 Bitcoin Historical USD Price (TS, NN, Keras)
📗 Time series DJIA 30 Stock (RNN, LSTM, GRU)

sibalex / data_analysis