def get(self, use_db, model_type, symbol, unit, count, period, partition, delta, seed, trees, jobs, longs): # If using db then validate db if use_db: @validate_db(db) def get_queries(): return [query_to_dict(q) for q in Data.query.all()] json = get_queries() else: json = None m = market.Market(json=json, symbol=symbol, unit=unit, count=count, period=period) features = m.set_features(partition=partition) features = m.set_long_features(features, columns_to_set=longs, partition=partition) targets = market.set_targets(features, delta=delta) features = features.drop(['close'], axis=1) model = market.setup_model(features[:-1], targets, model_type=model_type.lower(), seed=seed, n_estimators=trees, n_jobs=jobs) next_date = features.tail( 1) # Remember the entry we didn't train? Predict it. trend = market.target_code_to_name(model._predict_trends(next_date)[0]) accuracy = model.accuracy(model.features.test, model.targets.test) proba = model._predict_probas(next_date) proba_log = model._predict_logs(next_date) # Logarithmic scale return { 'trend': trend, 'test_set_accuracy': accuracy, 'probabilities': { market.target_code_to_name(code): p for code, p in enumerate(proba[0]) } }
def main(): args = get_args() assert args.partition > 0, 'The data must be partitioned!' m = market.Market(symbol=args.symbol, unit=args.unit, count=args.count, period=args.period) x = m.features(partition=args.partition) if args.long is not None: # Create long features DataFrame x_long = m.features(partition=2 * args.partition) # Remove features not specified by args.long unwanted_features = [f for f in x.columns if f not in args.long] x_long = x_long.drop(unwanted_features, axis=1) # Prefix long columns with 'long_' to fix naming conflicts x_long.columns = ['long_{0}'.format(f) for f in x_long.columns] # Merge the two DataFrames skip = args.partition x = pd.concat([x[skip:].reset_index(drop=True), x_long], axis=1) y = market.targets(x, delta=args.delta) x = x.drop(['close'], axis=1) model = market.setup_model(x[:-1], y, model_type=args.model.lower(), seed=args.seed, n_estimators=args.trees, n_jobs=args.jobs) next_date = x.tail(1) # Remember the entry we didn't train? Predict it. # TODO: Reimplement display of confusion matrix and feature importances acc = model.accuracy(model.features.test, model.targets.test) print('Test Set Accuracy: {0:.3f}%'.format(100 * acc)) trends = model._predict_trends(next_date) print('Predicted Trend: {0}'.format(market.target_code_to_name(trends[0]))) if args.proba: probas = model._predict_probas(next_date) print('Probability: {0}'.format(probas[0])) if args.proba_log: logs = model._predict_logs(next_date) print('Log Probability: {0}'.format(logs[0]))
def get(self, use_db, model, symbol, unit, count, period, partition, delta, seed, trees, jobs, longs): if use_db: db_json = None else: db_json = None m = market.Market(json=db_json, symbol=symbol, unit=unit, count=count, period=period) features = m.set_features(partition=partition) features = m.set_long_features(features, columns_to_set=longs, partition=partition) targets = market.set_targets(features, delta=delta) features = features.drop(['close'], axis=1) model = market.setup_model(features[:-1], targets, model_type=model.lower(), seed=seed, n_estimators=trees, n_jobs=jobs) next_date = features.tail( 1) # Remember the entry we didn't train? Predict it. trend = market.target_code_to_name(model._predict_trends(next_date)[0]) accuracy = model.accuracy(model.features.test, model.targets.test) proba = model._predict_probas(next_date) proba_log = model._predict_logs(next_date) # Logarithmic scale return { "trend": trend, "test_set_accuracy": accuracy, "probabilities": { market.target_code_to_name(code): p for code, p in enumerate(proba[0]) } }
def predict_coin(self, coin, unit, api, model_type): if api == 'spec': pcoin = 'USDT_' + coin.strip() coinmarket = market.Market(symbol=pcoin, unit=unit, count=6, period=86400) #Retrieve the x and y axises x = coinmarket.features(partition=14) y = market.targets(x, delta=25) #Get rid of the close stat because it is not useful at all. x = x.drop(['close'], axis=1) #Now create the random forest model or other one supported by the package model = market.setup_model(x[:-1], y, model_type=model_type, seed=1, n_estimators=65, n_jobs=4) # Predict the target test set from the features test set trends = model._predict_trends(model.features.test) # Get accuracies ftr_imps = model.feature_importances() conf_mx = model.confusion_matrix(model.targets.test, trends) acc = model.accuracy(model.features.test, model.targets.test) #Predictions and probabilities for the next trend next_date = x.tail(1) trends = model._predict_trends(next_date) pt = "The market for {} is predicted to be {}!".format( coin, market.target_code_to_name(trends[0])) probas = model._predict_probas(next_date) pr = 'Probability: {0}'.format(probas[0]) print(pr) logs = model._predict_logs(next_date) print('Log Probability: {0}'.format(logs[0])) return next_date, pt
def main(): args = get_args() assert args.partition > 0, 'The data must be partitioned!' m = market.Market(symbol=args.symbol, unit=args.unit, count=args.count, period=args.period) features = m.set_features(partition=args.partition) if args.long is not None: features = m.set_long_features(features, columns_to_set=args.long, partition=args.partition) targets = market.set_targets(features, delta=args.delta) features = features.drop(['close'], axis=1) model = market.setup_model(features[:-1], targets, model_type=args.model.lower(), seed=args.seed, n_estimators=args.trees, n_jobs=args.jobs) next_date = features.tail(1) # Remember the entry we didn't train? Predict it. # TODO: Reimplement display of confusion matrix and feature importances acc = model.accuracy(model.features.test, model.targets.test) print('Test Set Accuracy: {0:.3f}%'.format(100 * acc)) trends = model._predict_trends(next_date) print('Predicted Trend: {0}'.format(market.target_code_to_name(trends[0]))) if args.proba: probas = model._predict_probas(next_date) print('Probability: {0}'.format(probas[0])) if args.proba_log: logs = model._predict_logs(next_date) print('Log Probability: {0}'.format(logs[0]))
from speculator import market # Init market raw data m = market.Market(symbol='USDT_BTC', unit='month', count=6, period=86400) # Parse features, x axis x = m.features(partition=14) # Parse targets, y axis y = market.targets(x, delta=25) # Create the random forest model # The last entry doesn't have a target (can't predict yet), so skip over it model = market.setup_model(x[:-1], y, model_type='random_forest', seed=1, n_estimators=65, n_jobs=4) # Predict the target test set from the features test set pred = model.predict(model.features.test) # Get accuracies ftr_imps = model.feature_importances() conf_mx = model.confusion_matrix(model.targets.test, pred) acc = model.accuracy(model.targets.test, pred) # Display accuracies print('##################') print('# TEST SET #') print('##################')
def main(): args = get_args() m = market.Market(symbol=args.symbol, unit=args.unit, count=args.count, period=args.period) x = m.features(partition=args.partition) if args.long is not None: # Create long features DataFrame x_long = m.features(partition=2 * args.partition) # Remove features not specified by args.long unwanted_features = [f for f in x.columns if f not in args.long] x_long = x_long.drop(unwanted_features, axis=1) # Prefix long columns with 'long_' to fix naming conflicts x_long.columns = ['long_{0}'.format(f) for f in x_long.columns] # Merge the two DataFrames skip = args.partition x = pd.concat([x[skip:].reset_index(drop=True), x_long], axis=1) y = market.targets(x, delta=args.delta) x = x.drop(['close'], axis=1) model = market.setup_model(x[:-1], y, model_type=args.model, seed=args.seed, n_estimators=args.trees, n_jobs=args.jobs) # Predict the target test set from the features test set pred = model.predict(model.features.test) # Get accuracies ftr_imps = model.feature_importances() conf_mx = model.confusion_matrix(model.targets.test, pred) acc = model.accuracy(model.targets.test, pred) # Display accuracies print('##################') print('# TEST SET #') print('##################') print('Accuracy: {0:.3f}%'.format(100 * acc)) print('\nConfusion Matrix:') print(conf_mx) print(market.TARGET_CODES) print('\nFeature Importance:') for ftr, imp in ftr_imps: print(' {0}: {1:.3f}%'.format(ftr, 100 * imp)) print() # Display prediction and probabilities for the next trend print('##################') print('# PREDICTED NEXT #') print('##################') next_date = x.tail(1) # Remember the entry we didn't train? Predict it. trend = market.target_code_to_name(model.predict(next_date)[0]) print('Trend: {0}'.format(trend)) if args.proba: print('Probability: {0}'.format(model.predict_proba(next_date))) if args.proba_log: print('Log Probability: {0}'.format( model.predict_log_proba(next_date)))