diff --git a/2014-group28-PrzybylakHowellsDeng/.DS_Store b/2014-group28-PrzybylakHowellsDeng/.DS_Store new file mode 100644 index 0000000..c663397 Binary files /dev/null and b/2014-group28-PrzybylakHowellsDeng/.DS_Store differ diff --git a/2014-group28-PrzybylakHowellsDeng/code/Models.R b/2014-group28-PrzybylakHowellsDeng/code/Models.R new file mode 100644 index 0000000..7cd6de3 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/code/Models.R @@ -0,0 +1,89 @@ +#____________________ Decision Trees + + +controls <- rpart.control(minsplit = 1, minbucket = 5, cp = 0.001) #tree parameters +parms <- list(split = 'gini') #splitting methodology + + +CreateClassificationTree <- function(ch_discrDependentVariable, df_learnAttributes, df_learnDependentVariable, controls, parms) +{ + df_data <- cbind(df_learnDependentVariable, df_learnAttributes) + df_data <- data.frame(df_data) + + colnames(df_data) <- make.names(c(ch_discrDependentVariable,colnames(df_learnAttributes)), unique = TRUE, allow_ = TRUE) + + ch_explanatoryVariable <- paste(colnames(df_data[,-1]), "+", collapse = "", sep="") + formula <- paste(ch_discrDependentVariable," ~ ", ch_explanatoryVariable, sep="") + formula <- substr(formula, 1, nchar(formula) - 1) + tree <- rpart(eval(parse(t = formula)), data = df_data, + parms = parms, control = controls, method = "class") + + return(tree) +} + + +CPoptimal <- function(tree) #Pruning the tree to optimal size by complexity parameter (not used) +{ + + minpos <- min(seq_along(tree$cptable[,4])[tree$cptable[,4] == min(tree$cptable[,4])]) + minline <- tree$cptable[minpos,4] + tree$cptable[minpos,5] + xerror_min <- tree$cptable[,4] - minline + optimalCP_index <- min(seq_along(xerror_min)[xerror_min < 0]) + optimalCP <- tree$cptable[optimalCP_index,1] + + prunedTree <- prune(tree, optimalCP) + + return(prunedTree) +} + + +#____________________ RFs + + +CreateRF <- function(ch_discrDependentVariable, df_learnAttributes, df_learnDependentVariable, ntrees, + mtrys, nodesizes) +{ + df_data <- cbind(df_learnDependentVariable, df_learnAttributes) + df_data <- data.frame(df_data) + + colnames(df_data) <- make.names(c(ch_discrDependentVariable,colnames(df_learnAttributes)), unique = TRUE, allow_ = TRUE) + + ch_explanatoryVariable <- paste(colnames(df_data[,-1]), "+", collapse = "", sep="") + formula <- paste(ch_discrDependentVariable," ~ ", ch_explanatoryVariable, sep="") + formula <- substr(formula, 1, nchar(formula) - 1) + rf <- randomForest(eval(parse(t = formula)), na.action = na.omit,importance=TRUE, data = df_data, ntree = ntrees, + mtry = mtrys, nodesize = nodesizes) + + return(rf) +} + + +#____________________ LogisticRegresion + + +CreateLogistic <- function(ch_discrDependentVariable, df_learnAttributes, df_learnDependentVariable) +{ + + + df_data <- cbind(df_learnDependentVariable, df_learnAttributes) + df_data <- data.frame(df_data) + + colnames(df_data) <- make.names(c(ch_discrDependentVariable,colnames(df_learnAttributes)), unique = TRUE, allow_ = TRUE) + + ch_explanatoryVariable <- paste(colnames(df_data[,-1]), "+", collapse = "", sep="") + formula <- paste(ch_discrDependentVariable," ~ ", ch_explanatoryVariable, sep="") + formula <- substr(formula, 1, nchar(formula) - 1) + logistic <- glm(eval(parse(t = formula)), data = df_data, family=binomial(logit)) + + return(logistic) +} + + +#logistic <- CreateLogistic(colnames(labels), training_features, training_labels) #training labels haveto be {0,1} for logistic regression! +#tree <- CreateClassificationTree(colnames(MMM_label)[2], MMM_daily_features[1:20,c(2,3,4)], MMM_label[1:20,2], controls, parms) +#plot(tree); text(tree,use.n=T,cex=.5) + + + + +#table(prediction = class_predict , correct = MMM_label[21:32,2]) # Hitratio Matrix \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/code/ROC_functions.R b/2014-group28-PrzybylakHowellsDeng/code/ROC_functions.R new file mode 100644 index 0000000..ef09d82 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/code/ROC_functions.R @@ -0,0 +1,102 @@ +# CODE adapted from : http://web.expasy.org/pROC/screenshots.html +install.packages("pROC") +library(pROC) + +#data(aSAH) + + + + +#_____________________________ + + +pROC_AUC <- function(test_DV, pred, c_partial){ + + plot.roc(test_DV, pred, # data # (response, predictor) + + percent=TRUE, # show all values in percent + + partial.auc=c_partial, partial.auc.correct=TRUE, # define a partial AUC (pAUC) + + print.auc=TRUE, #display pAUC value on the plot with following options: + + print.auc.pattern=paste("Corrected pAUC (", c_partial[1],"-",c_partial[2]," %% SP):\n%.1f%%"), print.auc.col="#1c61b6", + + auc.polygon=TRUE, auc.polygon.col="#1c61b6", # show pAUC as a polygon + + max.auc.polygon=TRUE, max.auc.polygon.col="#1c61b622", # also show the 100% polygon + + main="Partial AUC (pAUC)") + + plot.roc(test_DV, pred, + + percent=TRUE, add=TRUE, type="n", # add to plot, but don't re-add the ROC itself (useless) + + partial.auc=c_partial, partial.auc.correct=TRUE, # define a partial AUC (pAUC) + + partial.auc.focus="se", # focus pAUC on the sensitivity + + print.auc=TRUE, print.auc.pattern=paste("Corrected pAUC (", c_partial[1],"-",c_partial[2]," %% SE):\n%.1f%%"), print.auc.col="#008600", #display pAUC value with options: + + print.auc.y=40, # do not print auc over the previous one + + auc.polygon=TRUE, auc.polygon.col="#008600", # show pAUC as a polygon + + max.auc.polygon=TRUE, max.auc.polygon.col="#00860022") # also show the 100% polygon + +} +#pROC_AUC(aSAH$outcome, aSAH$s100b,c(100,80)) # c(response,predictor) + +#____________________________ + +pROC_singlek <- function(test_DV, pred, th, method) { + + plot.roc(test_DV, pred, + + #main="Confidence interval of a threshold", percent=TRUE, + + main=method, percent=TRUE, + + ci=TRUE, of="thresholds", # compute AUC (of threshold) + + thresholds=th, # select the (best) threshold + + print.thres=th, # also highlight this threshold on the plot + + grid = TRUE, + + auc.polygon = TRUE) + +} + + +#pROC_singlek(aSAH$outcome, aSAH$s100b,"best") + +#____________________________ + +# ci.sp i ce.se w przedziale (0:100) zwracaja stochastycznie ten sam wykres. Są jednozancznie wyznacozne +# zacieniowany obszar rozjezdza sie troche z CI dla best boROC czase mjest stałą! w tym miejscu akurat jest. Czy tylko dlatego? + + +pROC_CI <- function(test_DV, pred) { + + rocobj <- plot.roc(test_DV, pred, + + main="Confidence intervals", percent=TRUE, + + ci=TRUE, # compute AUC (of AUC by default) + + print.auc=TRUE) + + ciobj <- ci.se(rocobj, # CI of sensitivity + + specificities=seq(0, 100, 5)) # over a select set of specificities + + plot(ciobj, type="shape", col="#1c61b6AA") # plot as a blue shape + + + plot(ci(rocobj, of="thresholds", thresholds="best")) # add one threshold + +} + +#pROC_CI(aSAH$outcome, aSAH$s100b) diff --git a/2014-group28-PrzybylakHowellsDeng/code/chart.py b/2014-group28-PrzybylakHowellsDeng/code/chart.py new file mode 100644 index 0000000..a9a81b1 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/code/chart.py @@ -0,0 +1,99 @@ +import statsmodels +import os +import numpy as np +import pandas as pd + +import matplotlib.pyplot as plt +import matplotlib.dates as mdates +import datetime as dt + +from sklearn.preprocessing import scale +from sklearn.preprocessing import Imputer +from sklearn.preprocessing import normalize + +def nan_helper(y): + """Helper to handle indices and logical indices of NaNs. + + Input: + - y, 1d numpy array with possible NaNs + Output: + - nans, logical indices of NaNs + - index, a function, with signature indices= index(logical_indices), + to convert logical indices of NaNs to 'equivalent' indices + Example: + >>> # linear interpolation of NaNs + >>> nans, x= nan_helper(y) + >>> y[nans]= np.interp(x(nans), x(~nans), y[~nans]) + """ + + return np.isnan(y), lambda z: z.nonzero()[0] + +os.chdir('/Users/jonathanhowells/Dropbox/IRDM-Twitter/alg1/') + +companies = ['boeing', '3m', 'caterpillar'] + +for company in companies: + folder = 'data/' + company + '/' + data = pd.read_csv(folder + company + 'share.csv') + y=data['Adj Close'].values + date = data['Date'].values + + + negative = data['Negative'].values + neutral = data['Neutral'].values + positive = data['Positive'].values + + nans, x= nan_helper(negative) + negative[nans]= np.interp(x(nans), x(~nans), negative[~nans]) + + nans, x= nan_helper(neutral) + neutral[nans]= np.interp(x(nans), x(~nans), neutral[~nans]) + + nans, x= nan_helper(positive) + positive[nans]= np.interp(x(nans), x(~nans), positive[~nans]) + + nans, x= nan_helper(y) + y[nans]= np.interp(x(nans), x(~nans), y[~nans]) + + + sentiment = np.column_stack((negative,neutral,positive)) + + sentiment + + sentiment_score = [] + + for i in range(sentiment.shape[0]): + score = (sentiment[i,2] - sentiment[i,0])/(sum(sentiment[i,:])) + sentiment_score.append(score) + + sentiment_score + + + x = [dt.datetime.strptime(d,'%d/%m/%Y').date() for d in date] + + fig, ax1 = plt.subplots() + y_norm = scale(y) + + plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%d/%m/%Y')) + plt.gca().xaxis.set_major_locator(mdates.AutoDateLocator()) + + ax1.plot(x,sentiment_score,'r-') + ax1.set_xlabel('Date') + ax1.set_ylabel('Sentiment', color='b') + + for tl in ax1.get_yticklabels(): + tl.set_color('b') + + ax2 = ax1.twinx() + ax2.plot(x, y, 'b-') + ax2.set_ylabel('Share Price', color='r') + for tl in ax2.get_yticklabels(): + tl.set_color('r') + + title = company + ' Share Price and Sentiment' + plt.title(title) + plt.legend() + plt.grid() + plt.gcf().autofmt_xdate() + plt.savefig(company + "graph") + plt.show() \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/code/main.R b/2014-group28-PrzybylakHowellsDeng/code/main.R new file mode 100644 index 0000000..471accd --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/code/main.R @@ -0,0 +1,135 @@ +# think about MLinterfaces, Ipred, carret + +library(rpart) +library(randomForest) +library(party) +library(lattice) +library(snowfall) # paralel multicore computations: http://journal.r-project.org/archive/2009-1/RJournal_2009-1_Knaus+et+al.pdf +library(TTR) + +setwd("C:\\Users\\user\\Desktop\\Information_Retrieval_and_Data_Mining\\IRDM") + +source("Rcode\\ROC_functions.R") +source("Rcode\\Models.R") + + +#______________ Data Preparation + +#____DAILY DATA + + +features <- read.table(c("Data//3mfeatures.txt"), header=FALSE, sep = "", quote = "'") #this is alreadydelay by 1 comparing to the label +features <- read.table(c("Data//caterpillarfeatures.txt"), header=FALSE, sep = "", quote = "'") #this is alreadydelay by 1 comparing to the label +features <- read.table(c("Data//boeingfeatures.txt"), header=FALSE, sep = "", quote = "'") #this is alreadydelay by 1 comparing to the label + +labels <- read.table(c("Data//3mtrend.txt"), header=FALSE, sep = "", quote = "'")[-1,2] #drop first observationto make it divisable for the CV procedure +labels <- read.table(c("Data//caterpillartrend.txt"), header=FALSE, sep = "", quote = "'")[-1,2] +labels <- read.table(c("Data//boeingtrend.txt"), header=FALSE, sep = "", quote = "'")[-1,2] + +labels <- as.data.frame(labels) +features <- features[-1,-1] #dropthe first observation to make the set divisable by 8 and drop thedate column + +features1 <- features +features1[,1] <- features[,1]/rowSums(features[,c(1:3)]) #positive ratio +features1[,2] <- features[,3]/rowSums(features[,c(1:3)]) #negative ratio +features1[,3] <- features[,2]/rowSums(features[,c(1:3)]) #neutral ratio +features1[,4] <- features[,1]/rowSums(features[,c(1,3)]) #positive to negative ratio +features1[,5] <-SMA(features1[,1],3) # 3 period moveing average of positiveratio +features1[,6] <-SMA(features1[,1],7) # 7 period moveing average of positiveratio +features1[,7] <-SMA(features1[,3],3) # 3 period moveing average of negative ratio +features1[,8] <-SMA(features1[,3],7) # 7 period moveing average of negative ratio +features1[,9] <- SMA(sign(c(0,diff(features1[,4]))),3) #guards against 1 very highjump, checks if the ratio of pos/neg is growing or declining recently + +features <- features1 +colnames(features) <- c("positive_ratio","negative_ratio","neutral_ratio","pos_neg","sma_pos3","sma_pos7","sma_neg3","sma_neg7","trend") + +#____HOURLY DATA + +features <- read.table(c("Data//3mhourfeaturesmatched.txt"), header=FALSE, sep = "", quote = "'") #this is alreadydelay by 1 comparing to the label +features <- read.table(c("Data//caterpillarhourfeaturesmatched.txt"), header=FALSE, sep = "", quote = "'") #this is alreadydelay by 1 comparing to the label +features <- read.table(c("Data//boeinghourfeaturesmatched.txt"), header=FALSE, sep = "", quote = "'") #this is alreadydelay by 1 comparing to the label + +features <- features[,2:4] + +labels <- read.table(c("Data//3mhourtrendmatched.txt"), header=FALSE, sep = "", quote = "'")[1:160,2] #drop first observationto make it divisable for the CV procedure +labels <- read.table(c("Data//caterpillarhourtrendmatched.txt"), header=FALSE, sep = "", quote = "'")[1:160,2] +labels <- read.table(c("Data//boeinghourtrendmatched.txt"), header=FALSE, sep = "", quote = "'")[,2] + +labels[labels== 0] <- 1 #treat no return as positive return +labels <- as.data.frame(labels) + + +####________ MODELS + + +RandomizedCV <- function(labels, features, method) +{ + c_remaining <- c(1:nrow(labels)) + predicted_prob <- numeric() + predicted_class <- numeric() + reordered_labels <- numeric() + + while(length(c_remaining) > 0) + { + c_hold_out <- sample(c_remaining, 4) + c_remaining <- c_remaining[! c_remaining %in% c_hold_out] + + training_labels <- labels[-c_hold_out,] + test_labels <- labels[c_hold_out,] + training_features <- features[-c_hold_out,] + test_features <- features[c_hold_out,] + reordered_labels <- c(reordered_labels, test_labels) + + + if(method=="tree") {model <- CreateClassificationTree(colnames(labels), training_features, training_labels, controls, parms) + } else if(method =="forest"){model <- CreateRF(colnames(labels), training_features, as.factor(training_labels), ntrees=2000, mtrys=2, nodesize = 1) + } else if(method =="logistic") + { + training_labels[training_labels == -1] <- 0 + model <- CreateLogistic(colnames(labels), training_features, training_labels) + } + + + if(method != "logistic") { + class_predict <- as.numeric(as.character(predict(model, test_features, type = 'class'))) + predicted_class <- c(predicted_class, class_predict)} + + if(method != "logistic"){prob_predict <- predict(model, test_features, type = 'prob')[,2]} else {prob_predict <- predict(model, test_features, type = 'response')} + predicted_prob <- c(predicted_prob, prob_predict) # append predictions from current iteration + + } + + + if(method != "logistic") {print(table(prediction = predicted_class , correct = reordered_labels))} # Hitratio Matrix + #pROC_AUC(reordered_labels, predicted_prob,c(0,0)) + pROC_singlek(reordered_labels, predicted_prob, "best", method) + +} + +#the optimal threshold is the average optimal threshold over all the cross-validations + +par(mfrow=c(1,3), pty="s", mar = c(0,0,0,0), oma=c(0.15,0.15,0.15,0.15)) +ktree <- RandomizedCV(labels, features, c("tree")) +kf0rest <- RandomizedCV(labels, features, c("forest")) #na.omit action is spurious! +klogistic <- RandomizedCV(labels, features, c("logistic")) +title( "3m hourly Results", outer = TRUE ) + +#RF1 <- CreateRF(colnames(MMM_label), training_features, as.factor(training_labels), ntrees=1000, mtrys=4, nodesize = 15) +#prob_predict <- predict(RF1, test_features,type = 'prob') + +###______VARIABLE IMPORTANCE FOR BEST MODEL + +bestrf <- CreateRF(colnames(labels), features, as.factor(labels[,1]), ntrees=2000, mtrys=3, nodesize = 1) +importance(bestrf,type=2,scale=FALSE) + +features1 <- features[,c(1,2,3,4,5,6,7)] + +labels1 <- labels +labels1[labels1 == -1] <- 0 +bestlog <- CreateLogistic(colnames(labels1), features1, labels1) + +#sentiment can not be expressed in one variable,therefor we create multiplevariables and let thepredictive models choosewhich +#variables bestdescribethe sentiment thatinfluences the market. + +table(prediction = predicted_class , correct = reordered_labels) +anova(bestlog,test="Chisq") \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/code/tweet.py b/2014-group28-PrzybylakHowellsDeng/code/tweet.py new file mode 100644 index 0000000..66fe4d8 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/code/tweet.py @@ -0,0 +1,182 @@ +""" +Parse json formated tweets file. +""" + +import re +import os, time, subprocess, shlex +import json + +def modifyFormat(): + """ + The original tweets json file is exampletweets_0.txt. It is in ill format. + Breaking each tweet into a single line and write to newtweets0.txt. + """ + fileName = 'data/exampletweets_0.txt' + fp = open(fileName) + content = fp.readline() + fp.close() + + pattern = r'}{"created_at":' + newContent = re.sub(pattern, '}\n{"created_at":', content) + + outFile = 'data/newtweets0.txt' + fp = open(outFile, 'w') + fp.write(newContent) + fp.close() + +def parseJson(): + """ + The original tweets json file (newtweets0.txt) is too large to read. So we extract + useful information and write into a small file (tweetsinfo.txt). + """ + fileName = 'data/newtweets0.txt' + fp = open(fileName) + lines = fp.readlines() + fp.close() + + outFile = 'data/tweetsinfo.txt' + fp = open(outFile, 'w') + print len(lines); + for i in xrange(0,len(lines)): + try: + data = json.loads(lines[i]) + text = data['text'].encode('utf8') + text = re.sub(r'\n', r' ', text) + date = data['created_at'].encode('utf8') + currTime = time.strptime(date, "%a %b %d %H:%M:%S +0000 %Y") + date = str(currTime.tm_mon) + '-' + str(currTime.tm_mday) + if i < len(lines)-1: + fp.write(date + " " + text + "\n") + else: + fp.write(date + " " + text) + except UnicodeDecodeError: + print i + fp.close() + +def splitByCorp(company): + """ + Splits tweetsinfo.txt by company name. + """ + # create a folder + folder = 'data/' + company + if not os.path.exists(folder): + os.makedirs(folder) + + fp = open('data/tweetsinfo.txt') + infoLines = fp.readlines() + fp.close() + + outFile = 'data/' + company + '/' + company + 'tweets.txt' + fp = open(outFile, 'w') + for i in xrange(0, len(infoLines)): + if re.search(r"%s" % company, infoLines[i], re.I): + fp.write(infoLines[i]) + fp.close() + +def splityByDate(company): + """ + Split tweets file of each company into smaller files by date. + """ + folder = 'data/' + company + '/split/' + if not os.path.exists(folder): + os.makedirs(folder) + + prefix = 'data/' + company + '/' + company + fp = open(prefix + 'tweets.txt') + lines = fp.readlines() + fp.close() + + date = '1-13' + fp = open(folder + date + '.txt', 'w') + for i in xrange(0,len(lines)): + temp = lines[i].split() + if temp[0] != date: + fp.close() + date = temp[0] + fp = open(folder + date + '.txt', 'w') + fp.write(lines[i]) + fp.close() + +def preprocess(): + """ + 1. Modify the format of the original tweets json file, which is in bad format. + 2. Extract 'created_at' and 'text' from tweets json file newtweets0.txt, + and write into a smaller file tweetsinfo.txt. + 3. Split tweetsinfo.txt into three files: boeingtweets.txt, caterpillartweets.txt + and 3mtweets.txt. Each file contains only information of that company. + 4. Split the above three files into smaller files by date. + """ + modifyFormat() + parseJson() + companies = ['boeing', 'caterpillar', '3m'] + for company in companies: + splitByCorp(company) + splityByDate(company) + +def sentiment(tweet): + """ + Perform sentiment analysis for some given text, using opinionfinder v2.0. + Input: + tweet -- text to be analysed. + Output: + negative -- number of negative words. + neutral -- number of neutral words. + positive -- number of positive words. + """ + os.chdir('opinionfinderv2.0') + fp = open('tweet/singletweet.txt', 'w') + fp.write(tweet) + fp.close() + + ofCmd = "java -Xmx1g -classpath ./lib/weka.jar:"\ + "./lib/stanford-postagger.jar:opinionfinder.jar "\ + "opin.main.RunOpinionFinder tweet.doclist -d "\ + "-r preprocessor,cluefinder,polarityclass" + subprocess.call(shlex.split(ofCmd), stdout=None) + + fp = open('tweet/singletweet.txt_auto_anns/exp_polarity.txt') + content = fp.read(); + fp.close() + negative = len(re.findall(r"negative", content)) + neutral = len(re.findall(r"neutral", content)) + positive = len(re.findall(r"positive", content)) + + os.chdir('..') + + return (negative, neutral, positive) + +def getFeatures(company): + """ + Apply sentiment analysis for all the tweets concerning that company, + find the number of negative, neutral and positive words on each day, + i.e., the features. And write the features into a file, such as, + data/boeing/boeingfeatures.txt. + """ + folder = 'data/' + company + '/' + fp = open(folder + company + 'features.txt', 'w') + fp.close() + + dates = [[13,14,15,16,20,21,22,23,26,27,28,29,30], \ + [2,3,4,5,6,9,10,11,12,13,17,18,19,20,23,24,25,26,27], [2]] + fefp = open(folder + company + 'features.txt', 'w+') + for month in xrange(1,4): + for day in dates[month-1]: + tweetFile = str(month) + '-' + str(day) + '.txt' + fp = open(folder + 'split/' + tweetFile) + content = fp.read() + fp.close() + (neg, neu, pos) = sentiment(content) + line = str(month) + "-" + str(day) + " " + str(neg) + " " \ + + str(neu) + " " + str(pos) + if month != 3 or day != dates[2][-1]: + line = line + '\n' + fefp.write(line) + fefp.close() + +if __name__ == '__main__': + start = time.time() + preprocess() + for company in ['boeing', '3m', 'caterpillar']: + getFeatures(company) + end = time.time() + print 'running time: %fs' % (end - start) diff --git a/2014-group28-PrzybylakHowellsDeng/code/tweethour.py b/2014-group28-PrzybylakHowellsDeng/code/tweethour.py new file mode 100644 index 0000000..00474c6 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/code/tweethour.py @@ -0,0 +1,227 @@ +""" +Parse json formated hourly-tweets file. +""" + +import re +import os, time, subprocess, shlex +import json + +def parseByHour(): + """ + Extract twitter text and date. Then write into tweetshourinfo.txt. + """ + fileName = 'data/newtweets0.txt' + fp = open(fileName) + lines = fp.readlines() + fp.close() + + outFile = 'data/tweetshourinfo.txt' + fp = open(outFile, 'w') + print len(lines); + for i in xrange(0,len(lines)): + try: + data = json.loads(lines[i]) + text = data['text'].encode('utf8') + text = re.sub(r'\n', r' ', text) + date = data['created_at'].encode('utf8') + currTime = time.strptime(date, "%a %b %d %H:%M:%S +0000 %Y") + date = str(currTime.tm_mon) + '-' + str(currTime.tm_mday) + "-" + str(currTime.tm_hour) + if i < len(lines)-1: + fp.write(date + " " + text + "\n") + else: + fp.write(date + " " + text) + except UnicodeDecodeError: + print i + fp.close() + +def splitByCorp(company): + """ + Splits tweetsinfo.txt by company name. + """ + # create a folder + folder = 'data/' + company + if not os.path.exists(folder): + os.makedirs(folder) + + fp = open('data/tweetshourinfo.txt') + infoLines = fp.readlines() + fp.close() + + outFile = 'data/' + company + '/' + company + 'tweetshour.txt' + fp = open(outFile, 'w') + for i in xrange(0, len(infoLines)): + if re.search(r"%s" % company, infoLines[i], re.I): + fp.write(infoLines[i]) + fp.close() + +def splityByDate(company): + """ + Split tweets file of each company into smaller files by date. + """ + folder = 'data/' + company + '/splithour/' + if not os.path.exists(folder): + os.makedirs(folder) + + prefix = 'data/' + company + '/' + company + fp = open(prefix + 'tweetshour.txt') + lines = fp.readlines() + fp.close() + + date = '1-13-20' + fp = open(folder + date + '.txt', 'w') + for i in xrange(0,len(lines)): + temp = lines[i].split() + if temp[0] != date: + fp.close() + date = temp[0] + fp = open(folder + date + '.txt', 'w') + fp.write(lines[i]) + fp.close() + +def preprocess(): + """ + 1. Extract 'created_at' and 'text' from tweets json file newtweets0.txt, + and write into a smaller file tweetsinfo.txt. + 2. Split tweetsinfo.txt into three files: boeingtweets.txt, caterpillartweets.txt + and 3mtweets.txt. Each file contains only information of that company. + 3. Split the above three files into smaller files by date. + """ + parseByHour() + companies = ['boeing', 'caterpillar', '3m'] + for company in companies: + splitByCorp(company) + splityByDate(company) + +def sentiment(tweet): + """ + Perform sentiment analysis for some given text, using opinionfinder v2.0. + Input: + tweet -- text to be analysed. + Output: + negative -- number of negative words. + neutral -- number of neutral words. + positive -- number of positive words. + """ + os.chdir('opinionfinderv2.0') + fp = open('tweet/singletweet.txt', 'w') + fp.write(tweet) + fp.close() + + ofCmd = "java -Xmx1g -classpath ./lib/weka.jar:"\ + "./lib/stanford-postagger.jar:opinionfinder.jar "\ + "opin.main.RunOpinionFinder tweet.doclist -d "\ + "-r preprocessor,cluefinder,polarityclass" + subprocess.call(shlex.split(ofCmd), stdout=None) + + fp = open('tweet/singletweet.txt_auto_anns/exp_polarity.txt') + content = fp.read(); + fp.close() + negative = len(re.findall(r"negative", content)) + neutral = len(re.findall(r"neutral", content)) + positive = len(re.findall(r"positive", content)) + + os.chdir('..') + + return (negative, neutral, positive) + +def getFeatures(company): + """ + Apply sentiment analysis for all the tweets concerning that company, + find the number of negative, neutral and positive words on each day, + i.e., the features. And write the features into a file, such as, + data/boeing/boeinghourfeatures.txt. + """ + folder = 'data/' + company + '/' + fp = open(folder + company + 'hourfeatures.txt', 'w') + fp.close() + + dates = [[13,14,15,16,20,21,22,23,26,27,28,29,30], \ + [2,3,4,5,6,9,10,11,12,13,17,18,19,20,23,24,25,26,27], [2]] + hours = [15,16,17,18,19,20,21] + fefp = open(folder + company + 'hourfeatures.txt', 'w+') + for month in xrange(1,4): + for day in dates[month-1]: + for hour in hours: + tweetFile = str(month) + '-' + str(day) + '-' + str(hour) + '.txt' + try: + fp = open(folder + 'splithour/' + tweetFile) + content = fp.read() + fp.close() + (neg, neu, pos) = sentiment(content) + line = str(month) + "-" + str(day) + '-' + str(hour) + " " + str(neg) + " " \ + + str(neu) + " " + str(pos) + if month != 3 or day != dates[2][-1]: + line = line + '\n' + fefp.write(line) + except: + print tweetFile + pass + fefp.close() + +def compareTime(time1, time2): + (month1, day1, hour1) = time1.split('-') + (month1, day1, hour1) = (int(month1), int(day1), int(hour1)) + (month2, day2, hour2) = time2.split('-') + (month2, day2, hour2) = (int(month2), int(day2), int(hour2)) + if month1 < month2: + return -1 + elif month1 == month2: + if day1 < day2: + return -1 + elif day1 == day2: + if hour1 < hour2-1: + return -1 + elif hour1 == hour2-1: + return 0 + else: + return 1 + else: + return 1 + else: + return 1 + +def match(company): + """ + Match the hour feature and trend by time, because some data is missing. + """ + folder = 'data/' + company + '/' + + fp = open(folder + company + 'hourfeatures.txt') + featureLine = fp.readlines() + fp.close() + + fp = open(folder + company + 'hourtrend.txt') + trendLine = fp.readlines() + fp.close() + + fp1 = open(folder + company + 'hourfeaturesmatched.txt', 'w') + fp2 = open(folder + company + 'hourtrendmatched.txt', 'w') + + index1 = 0 + index2 = 0 + while index1 < len(featureLine) and index2 < len(trendLine): + feature = featureLine[index1] + trend = trendLine[index2] + comp = compareTime(feature.split()[0], trend.split()[0]) + if comp == 0: + fp1.write(feature) + fp2.write(trend) + index1 += 1 + index2 += 1 + elif comp < 0: + index1 += 1 + else: + index2 += 1 + + fp1.close() + fp2.close() + +if __name__ == '__main__': + start = time.time() + # preprocess() + # for company in ['boeing', '3m', 'caterpillar']: + # getFeatures(company) + for company in ['3m', 'caterpillar']: + match(company) + end = time.time() + print 'running time: %fs' % (end - start) diff --git a/2014-group28-PrzybylakHowellsDeng/data/3m/3menglishfeatures.txt b/2014-group28-PrzybylakHowellsDeng/data/3m/3menglishfeatures.txt new file mode 100644 index 0000000..7e62cb1 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/3m/3menglishfeatures.txt @@ -0,0 +1,33 @@ +1-13 0 14 1 +1-14 263 4304 194 +1-15 134 1015 48 +1-16 151 1238 210 +1-20 180 2331 208 +1-21 106 1302 147 +1-22 21 124 11 +1-23 80 443 66 +1-26 467 4162 380 +1-27 240 1009 185 +1-28 271 1038 75 +1-29 94 718 48 +1-30 106 633 100 +2-2 179 639 51 +2-3 13 107 17 +2-4 266 2515 249 +2-5 334 3063 189 +2-6 1860 8498 944 +2-9 83 940 66 +2-10 0 8 1 +2-11 157 159 51 +2-12 105 949 96 +2-13 169 1862 103 +2-17 123 1372 133 +2-18 657 5373 661 +2-19 617 5168 546 +2-20 957 6518 1027 +2-23 314 3351 320 +2-24 137 1168 99 +2-25 731 1444 155 +2-26 175 1106 89 +2-27 356 1139 145 +3-2 611 1804 159 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/3m/3mfeatures.txt b/2014-group28-PrzybylakHowellsDeng/data/3m/3mfeatures.txt new file mode 100644 index 0000000..53016cc --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/3m/3mfeatures.txt @@ -0,0 +1,33 @@ +1-13 0 14 1 +1-14 331 4656 261 +1-15 154 1078 73 +1-16 193 1268 277 +1-20 237 2590 254 +1-21 120 1449 159 +1-22 146 1225 284 +1-23 117 1675 132 +1-26 548 4510 443 +1-27 275 1277 190 +1-28 333 1134 107 +1-29 95 2052 161 +1-30 121 1266 146 +2-2 39 173 18 +2-3 176 1753 221 +2-4 97 2226 106 +2-5 363 3224 225 +2-6 2225 8691 1247 +2-9 78 1061 60 +2-10 0 8 1 +2-11 152 176 49 +2-12 141 1048 117 +2-13 173 1961 157 +2-17 162 1476 150 +2-18 721 5798 766 +2-19 295 1894 244 +2-20 1234 6881 1089 +2-23 367 3906 314 +2-24 184 1243 122 +2-25 766 1490 220 +2-26 187 1148 140 +2-27 356 1244 190 +3-2 725 1773 176 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourfeatures.txt b/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourfeatures.txt new file mode 100644 index 0000000..51eca00 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourfeatures.txt @@ -0,0 +1,212 @@ +1-13-20 0 14 1 +1-14-15 28 314 18 +1-14-16 23 276 12 +1-14-17 29 322 15 +1-14-18 41 411 29 +1-14-19 39 317 26 +1-14-20 43 227 21 +1-14-21 15 216 10 +1-15-15 17 236 15 +1-15-16 41 336 151 +1-15-17 25 1055 58 +1-15-18 39 816 35 +1-15-19 20 480 40 +1-15-20 25 333 55 +1-15-21 24 369 16 +1-16-15 27 358 27 +1-16-16 23 322 22 +1-16-17 33 213 14 +1-16-18 21 455 9 +1-16-19 12 216 8 +1-16-20 13 246 7 +1-16-21 25 158 13 +1-20-15 33 248 20 +1-20-16 24 252 10 +1-20-17 8 178 10 +1-20-18 10 416 15 +1-20-19 26 286 41 +1-20-20 20 237 14 +1-20-21 33 206 15 +1-21-15 11 206 7 +1-21-16 15 245 13 +1-21-17 11 283 26 +1-21-18 25 241 17 +1-21-19 77 385 22 +1-21-20 12 333 22 +1-21-21 8 270 18 +1-22-15 33 252 9 +1-22-16 26 211 15 +1-22-17 14 243 24 +1-22-18 35 303 17 +1-22-19 39 283 21 +1-22-20 13 227 35 +1-22-21 12 289 19 +1-26-15 18 137 13 +1-26-16 12 173 24 +1-26-17 13 291 22 +1-26-18 10 215 9 +1-26-19 9 194 5 +1-26-20 17 192 23 +1-26-21 25 184 17 +1-27-15 37 288 26 +1-27-16 13 357 29 +1-27-17 29 273 29 +1-27-18 43 715 53 +1-27-19 17 610 60 +1-27-20 27 367 16 +1-27-21 27 329 41 +1-28-15 23 301 26 +1-28-16 12 221 51 +1-28-17 20 652 18 +1-28-18 18 420 16 +1-28-19 26 369 19 +1-28-20 21 221 21 +1-28-21 51 254 15 +1-29-15 15 363 36 +1-29-16 35 383 34 +1-29-17 29 306 31 +1-29-18 17 284 19 +1-29-19 11 299 23 +1-29-20 19 264 24 +1-29-21 62 215 29 +1-30-15 33 429 22 +1-30-16 19 525 108 +1-30-17 20 449 113 +1-30-18 16 297 19 +1-30-19 31 412 21 +1-30-20 27 380 30 +1-30-21 24 547 57 +2-2-15 7 167 12 +2-2-16 21 211 16 +2-2-17 16 219 17 +2-2-18 12 204 18 +2-2-19 7 208 17 +2-2-20 23 216 12 +2-2-21 22 192 11 +2-3-15 56 281 22 +2-3-16 23 301 14 +2-3-17 18 261 22 +2-3-18 20 280 24 +2-3-19 12 2294 11 +2-3-20 7 1410 17 +2-3-21 35 1509 14 +2-4-15 23 729 19 +2-4-16 17 827 61 +2-4-17 28 718 41 +2-4-18 22 533 21 +2-4-19 325 568 32 +2-4-20 209 834 29 +2-4-21 294 1128 212 +2-5-15 84 722 94 +2-5-16 24 537 35 +2-5-17 18 275 33 +2-5-18 17 317 76 +2-5-19 21 394 13 +2-5-20 10 447 10 +2-5-21 57 474 45 +2-6-15 98 417 44 +2-6-16 72 467 109 +2-6-17 32 331 47 +2-6-18 51 308 35 +2-6-19 30 381 25 +2-6-20 20 416 47 +2-6-21 77 448 34 +2-9-15 16 151 26 +2-9-16 7 140 7 +2-9-17 10 205 32 +2-9-18 23 231 39 +2-9-19 18 162 14 +2-9-20 9 194 16 +2-9-21 264 779 508 +2-10-15 25 322 22 +2-10-16 15 245 13 +2-10-17 29 387 22 +2-10-18 23 196 17 +2-10-19 20 235 32 +2-10-20 31 236 43 +2-10-21 25 266 27 +2-11-15 13 266 10 +2-11-16 18 226 13 +2-11-17 30 232 20 +2-11-18 17 252 22 +2-11-19 14 269 22 +2-11-20 12 375 23 +2-11-21 11 329 28 +2-12-15 54 387 29 +2-12-16 24 278 14 +2-12-17 30 282 17 +2-12-18 31 223 27 +2-12-19 9 221 44 +2-12-20 26 257 11 +2-12-21 22 281 21 +2-13-15 13 405 21 +2-13-16 26 279 16 +2-13-17 12 298 21 +2-13-18 20 221 21 +2-13-19 14 252 21 +2-13-20 21 235 18 +2-13-21 13 196 13 +2-17-15 17 295 8 +2-17-16 22 394 54 +2-17-17 16 262 16 +2-17-18 47 398 20 +2-17-19 21 260 27 +2-17-20 20 316 43 +2-17-21 16 241 19 +2-18-15 11 382 35 +2-18-16 66 413 55 +2-18-17 30 235 27 +2-18-18 23 312 31 +2-18-19 9 342 21 +2-18-20 26 377 85 +2-18-21 45 489 44 +2-19-15 28 254 55 +2-19-16 24 306 16 +2-19-17 6 267 36 +2-19-18 29 159 28 +2-19-19 12 227 20 +2-19-20 16 333 12 +2-19-21 15 247 43 +2-20-15 18 240 20 +2-20-16 44 507 46 +2-20-17 28 444 94 +2-20-18 60 430 62 +2-20-19 35 417 67 +2-20-20 547 1187 338 +2-20-21 146 484 86 +2-23-15 11 189 4 +2-23-16 51 233 13 +2-23-17 7 207 1 +2-23-18 21 219 28 +2-23-19 14 194 14 +2-23-20 5 148 5 +2-23-21 17 184 23 +2-24-15 10 148 16 +2-24-16 26 238 28 +2-24-17 25 245 21 +2-24-18 28 218 45 +2-24-19 27 272 31 +2-24-20 27 312 64 +2-24-21 22 227 11 +2-25-15 81 280 27 +2-25-16 65 295 38 +2-25-17 117 272 42 +2-25-18 56 292 45 +2-25-19 33 391 31 +2-25-20 36 272 41 +2-25-21 39 239 15 +2-26-15 144 824 154 +2-26-16 296 845 280 +2-26-17 26 477 42 +2-26-18 15 438 32 +2-26-19 41 379 19 +2-26-20 27 347 28 +2-26-21 68 514 54 +2-27-15 18 255 18 +2-27-16 9 288 11 +2-27-17 24 379 39 +2-27-18 24 320 58 +2-27-19 14 435 19 +2-27-20 8 335 13 +2-27-21 18 291 26 +3-2-15 20 239 113-2-16 21 195 133-2-17 11 169 43-2-18 26 199 153-2-19 14 228 183-2-20 15 216 273-2-21 6 226 6 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourfeaturesmatched.txt b/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourfeaturesmatched.txt new file mode 100644 index 0000000..e0b6a51 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourfeaturesmatched.txt @@ -0,0 +1,160 @@ +1-15-16 41 336 151 +1-15-17 25 1055 58 +1-15-18 39 816 35 +1-15-19 20 480 40 +1-15-20 25 333 55 +1-15-21 24 369 16 +1-16-15 27 358 27 +1-16-16 23 322 22 +1-16-17 33 213 14 +1-16-18 21 455 9 +1-16-19 12 216 8 +1-16-20 13 246 7 +1-16-21 25 158 13 +1-21-15 11 206 7 +1-21-16 15 245 13 +1-21-17 11 283 26 +1-21-18 25 241 17 +1-21-19 77 385 22 +1-21-20 12 333 22 +1-21-21 8 270 18 +1-22-15 33 252 9 +1-22-16 26 211 15 +1-22-17 14 243 24 +1-22-18 35 303 17 +1-22-19 39 283 21 +1-22-20 13 227 35 +1-22-21 12 289 19 +1-27-15 37 288 26 +1-27-16 13 357 29 +1-27-17 29 273 29 +1-27-18 43 715 53 +1-27-19 17 610 60 +1-27-20 27 367 16 +1-27-21 27 329 41 +1-28-15 23 301 26 +1-28-16 12 221 51 +1-28-17 20 652 18 +1-28-18 18 420 16 +1-28-19 26 369 19 +1-28-20 21 221 21 +1-28-21 51 254 15 +1-29-15 15 363 36 +1-29-16 35 383 34 +1-29-17 29 306 31 +1-29-18 17 284 19 +1-29-19 11 299 23 +1-29-20 19 264 24 +1-29-21 62 215 29 +1-30-15 33 429 22 +1-30-16 19 525 108 +1-30-17 20 449 113 +1-30-18 16 297 19 +1-30-19 31 412 21 +1-30-20 27 380 30 +1-30-21 24 547 57 +2-3-15 56 281 22 +2-3-16 23 301 14 +2-3-17 18 261 22 +2-3-18 20 280 24 +2-3-19 12 2294 11 +2-3-20 7 1410 17 +2-3-21 35 1509 14 +2-4-15 23 729 19 +2-4-16 17 827 61 +2-4-17 28 718 41 +2-4-18 22 533 21 +2-4-19 325 568 32 +2-4-20 209 834 29 +2-4-21 294 1128 212 +2-5-15 84 722 94 +2-5-16 24 537 35 +2-5-17 18 275 33 +2-5-18 17 317 76 +2-5-19 21 394 13 +2-5-20 10 447 10 +2-5-21 57 474 45 +2-6-15 98 417 44 +2-6-16 72 467 109 +2-6-17 32 331 47 +2-6-18 51 308 35 +2-6-19 30 381 25 +2-6-20 20 416 47 +2-6-21 77 448 34 +2-10-15 25 322 22 +2-10-16 15 245 13 +2-10-17 29 387 22 +2-10-18 23 196 17 +2-10-19 20 235 32 +2-10-20 31 236 43 +2-10-21 25 266 27 +2-11-15 13 266 10 +2-11-16 18 226 13 +2-11-17 30 232 20 +2-11-18 17 252 22 +2-11-19 14 269 22 +2-11-20 12 375 23 +2-11-21 11 329 28 +2-12-15 54 387 29 +2-12-16 24 278 14 +2-12-17 30 282 17 +2-12-18 31 223 27 +2-12-19 9 221 44 +2-12-20 26 257 11 +2-12-21 22 281 21 +2-13-15 13 405 21 +2-13-16 26 279 16 +2-13-17 12 298 21 +2-13-18 20 221 21 +2-13-19 14 252 21 +2-13-20 21 235 18 +2-13-21 13 196 13 +2-18-15 11 382 35 +2-18-16 66 413 55 +2-18-17 30 235 27 +2-18-18 23 312 31 +2-18-19 9 342 21 +2-18-20 26 377 85 +2-18-21 45 489 44 +2-19-15 28 254 55 +2-19-16 24 306 16 +2-19-17 6 267 36 +2-19-18 29 159 28 +2-19-19 12 227 20 +2-19-20 16 333 12 +2-19-21 15 247 43 +2-20-15 18 240 20 +2-20-16 44 507 46 +2-20-17 28 444 94 +2-20-18 60 430 62 +2-20-19 35 417 67 +2-20-20 547 1187 338 +2-20-21 146 484 86 +2-24-15 10 148 16 +2-24-16 26 238 28 +2-24-17 25 245 21 +2-24-18 28 218 45 +2-24-19 27 272 31 +2-24-20 27 312 64 +2-24-21 22 227 11 +2-25-15 81 280 27 +2-25-16 65 295 38 +2-25-17 117 272 42 +2-25-18 56 292 45 +2-25-19 33 391 31 +2-25-20 36 272 41 +2-25-21 39 239 15 +2-26-15 144 824 154 +2-26-16 296 845 280 +2-26-17 26 477 42 +2-26-18 15 438 32 +2-26-19 41 379 19 +2-26-20 27 347 28 +2-26-21 68 514 54 +2-27-15 18 255 18 +2-27-16 9 288 11 +2-27-17 24 379 39 +2-27-18 24 320 58 +2-27-19 14 435 19 +2-27-20 8 335 13 +2-27-21 18 291 26 diff --git a/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourtrend.txt b/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourtrend.txt new file mode 100644 index 0000000..c2717a3 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourtrend.txt @@ -0,0 +1,426 @@ +1-15-17 1 +1-15-18 -1 +1-15-19 -1 +1-15-20 1 +1-15-21 1 +1-15-22 -1 +1-16-16 1 +1-16-17 -1 +1-16-18 -1 +1-16-19 1 +1-16-20 -1 +1-16-21 -1 +1-16-22 1 +1-17-16 -1 +1-17-17 -1 +1-17-18 0 +1-17-19 1 +1-17-20 -1 +1-17-21 -1 +1-17-22 -1 +1-21-16 1 +1-21-17 -1 +1-21-18 -1 +1-21-19 1 +1-21-20 1 +1-21-21 1 +1-21-22 -1 +1-22-16 -1 +1-22-17 -1 +1-22-18 1 +1-22-19 1 +1-22-20 1 +1-22-21 -1 +1-22-22 -1 +1-23-16 -1 +1-23-17 -1 +1-23-18 1 +1-23-19 -1 +1-23-20 -1 +1-23-21 1 +1-23-22 1 +1-24-16 -1 +1-24-17 -1 +1-24-18 -1 +1-24-19 -1 +1-24-20 -1 +1-24-21 -1 +1-24-22 -1 +1-27-16 1 +1-27-17 -1 +1-27-18 -1 +1-27-19 -1 +1-27-20 1 +1-27-21 1 +1-27-22 -1 +1-28-16 1 +1-28-17 -1 +1-28-18 -1 +1-28-19 1 +1-28-20 -1 +1-28-21 1 +1-28-22 1 +1-29-16 1 +1-29-17 1 +1-29-18 1 +1-29-19 -1 +1-29-20 -1 +1-29-21 -1 +1-29-22 1 +1-30-16 -1 +1-30-17 -1 +1-30-18 1 +1-30-19 -1 +1-30-20 -1 +1-30-21 -1 +1-30-22 1 +1-31-16 -1 +1-31-17 -1 +1-31-18 1 +1-31-19 1 +1-31-20 1 +1-31-21 1 +1-31-22 -1 +2-3-16 -1 +2-3-17 -1 +2-3-18 -1 +2-3-19 -1 +2-3-20 -1 +2-3-21 -1 +2-3-22 -1 +2-4-16 1 +2-4-17 1 +2-4-18 1 +2-4-19 1 +2-4-20 -1 +2-4-21 1 +2-4-22 -1 +2-5-16 -1 +2-5-17 1 +2-5-18 1 +2-5-19 1 +2-5-20 -1 +2-5-21 -1 +2-5-22 -1 +2-6-16 1 +2-6-17 1 +2-6-18 1 +2-6-19 1 +2-6-20 1 +2-6-21 1 +2-6-22 1 +2-7-16 1 +2-7-17 -1 +2-7-18 1 +2-7-19 1 +2-7-20 1 +2-7-21 -1 +2-7-22 1 +2-10-16 -1 +2-10-17 -1 +2-10-18 -1 +2-10-19 1 +2-10-20 -1 +2-10-21 1 +2-10-22 -1 +2-11-16 1 +2-11-17 1 +2-11-18 1 +2-11-19 -1 +2-11-20 1 +2-11-21 1 +2-11-22 -1 +2-12-16 1 +2-12-17 -1 +2-12-18 1 +2-12-19 -1 +2-12-20 -1 +2-12-21 -1 +2-12-22 1 +2-13-16 -1 +2-13-17 1 +2-13-18 1 +2-13-19 -1 +2-13-20 1 +2-13-21 -1 +2-13-22 1 +2-14-16 1 +2-14-17 1 +2-14-18 1 +2-14-19 1 +2-14-20 1 +2-14-21 1 +2-14-22 1 +2-18-16 1 +2-18-17 -1 +2-18-18 1 +2-18-19 -1 +2-18-20 -1 +2-18-21 -1 +2-18-22 -1 +2-19-16 1 +2-19-17 -1 +2-19-18 -1 +2-19-19 -1 +2-19-20 1 +2-19-21 -1 +2-19-22 -1 +2-20-16 -1 +2-20-17 1 +2-20-18 1 +2-20-19 1 +2-20-20 1 +2-20-21 1 +2-20-22 -1 +2-21-16 1 +2-21-17 -1 +2-21-18 1 +2-21-19 -1 +2-21-20 -1 +2-21-21 -1 +2-21-22 -1 +2-24-16 1 +2-24-17 1 +2-24-18 1 +2-24-19 -1 +2-24-20 -1 +2-24-21 1 +2-24-22 -1 +2-25-16 -1 +2-25-17 1 +2-25-18 1 +2-25-19 1 +2-25-20 -1 +2-25-21 -1 +2-25-22 -1 +2-26-16 1 +2-26-17 -1 +2-26-18 1 +2-26-19 -1 +2-26-20 1 +2-26-21 -1 +2-26-22 1 +2-27-16 1 +2-27-17 1 +2-27-18 1 +2-27-19 -1 +2-27-20 1 +2-27-21 -1 +2-27-22 1 +2-28-16 1 +2-28-17 1 +2-28-18 1 +2-28-19 -1 +2-28-20 1 +2-28-21 -1 +2-28-22 -1 +3-3-16 -1 +3-3-17 -1 +3-3-18 -1 +3-3-19 1 +3-3-20 1 +3-3-21 -1 +3-3-22 1 +3-4-16 -1 +3-4-17 1 +3-4-18 1 +3-4-19 -1 +3-4-20 1 +3-4-21 -1 +3-4-22 1 +3-5-16 1 +3-5-17 -1 +3-5-18 1 +3-5-19 1 +3-5-20 -1 +3-5-21 1 +3-5-22 -1 +3-6-16 1 +3-6-17 -1 +3-6-18 1 +3-6-19 -1 +3-6-20 -1 +3-6-21 1 +3-6-22 -1 +3-7-16 1 +3-7-17 -1 +3-7-18 -1 +3-7-19 1 +3-7-20 -1 +3-7-21 -1 +3-7-22 -1 +3-10-15 -1 +3-10-16 -1 +3-10-17 1 +3-10-18 1 +3-10-19 -1 +3-10-20 1 +3-10-21 -1 +3-11-15 -1 +3-11-16 1 +3-11-17 -1 +3-11-18 -1 +3-11-19 -1 +3-11-20 -1 +3-11-21 1 +3-12-15 -1 +3-12-16 1 +3-12-17 1 +3-12-18 1 +3-12-19 -1 +3-12-20 1 +3-12-21 1 +3-13-15 1 +3-13-16 -1 +3-13-17 -1 +3-13-18 -1 +3-13-19 -1 +3-13-20 -1 +3-13-21 -1 +3-14-15 -1 +3-14-16 1 +3-14-17 1 +3-14-18 -1 +3-14-19 -1 +3-14-20 -1 +3-14-21 -1 +3-17-15 1 +3-17-16 -1 +3-17-17 1 +3-17-18 1 +3-17-19 -1 +3-17-20 1 +3-17-21 -1 +3-18-15 1 +3-18-16 1 +3-18-17 1 +3-18-18 -1 +3-18-19 1 +3-18-20 0 +3-18-21 -1 +3-19-15 1 +3-19-16 -1 +3-19-17 -1 +3-19-18 1 +3-19-19 -1 +3-19-20 -1 +3-19-21 -1 +3-20-15 1 +3-20-16 1 +3-20-17 1 +3-20-18 1 +3-20-19 -1 +3-20-20 -1 +3-20-21 1 +3-21-15 1 +3-21-16 -1 +3-21-17 1 +3-21-18 1 +3-21-19 -1 +3-21-20 1 +3-21-21 -1 +3-24-15 -1 +3-24-16 -1 +3-24-17 -1 +3-24-18 -1 +3-24-19 1 +3-24-20 1 +3-24-21 -1 +3-25-15 1 +3-25-16 -1 +3-25-17 1 +3-25-18 1 +3-25-19 1 +3-25-20 1 +3-25-21 1 +3-26-15 1 +3-26-16 -1 +3-26-17 1 +3-26-18 1 +3-26-19 -1 +3-26-20 1 +3-26-21 -1 +3-27-15 -1 +3-27-16 1 +3-27-17 -1 +3-27-18 1 +3-27-19 -1 +3-27-20 -1 +3-27-21 1 +3-28-15 1 +3-28-16 -1 +3-28-17 1 +3-28-18 1 +3-28-19 -1 +3-28-20 -1 +3-28-21 1 +3-31-16 1 +3-31-17 1 +3-31-18 -1 +3-31-19 1 +3-31-20 -1 +3-31-21 -1 +3-31-22 1 +4-1-16 1 +4-1-17 -1 +4-1-18 1 +4-1-19 1 +4-1-20 1 +4-1-21 1 +4-1-22 1 +4-2-16 -1 +4-2-17 1 +4-2-18 -1 +4-2-19 1 +4-2-20 -1 +4-2-21 1 +4-2-22 1 +4-3-16 1 +4-3-17 -1 +4-3-18 -1 +4-3-19 -1 +4-3-20 1 +4-3-21 -1 +4-3-22 1 +4-4-16 1 +4-4-17 1 +4-4-18 -1 +4-4-19 -1 +4-4-20 1 +4-4-21 -1 +4-4-22 -1 +4-7-16 -1 +4-7-17 -1 +4-7-18 -1 +4-7-19 1 +4-7-20 -1 +4-7-21 1 +4-7-22 -1 +4-8-16 -1 +4-8-17 1 +4-8-18 1 +4-8-19 -1 +4-8-20 1 +4-8-21 -1 +4-8-22 1 +4-9-16 -1 +4-9-17 1 +4-9-18 -1 +4-9-19 0 +4-9-20 1 +4-9-21 1 +4-9-22 1 +4-10-16 1 +4-10-17 1 +4-10-18 -1 +4-10-19 -1 +4-10-20 1 +4-10-21 -1 +4-10-22 -1 +4-11-16 -1 +4-11-17 1 +4-11-18 -1 +4-11-19 -1 +4-11-20 -1 +4-11-21 0 +4-11-22 -1 diff --git a/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourtrendmatched.txt b/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourtrendmatched.txt new file mode 100644 index 0000000..5518478 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/3m/3mhourtrendmatched.txt @@ -0,0 +1,160 @@ +1-15-17 1 +1-15-18 -1 +1-15-19 -1 +1-15-20 1 +1-15-21 1 +1-15-22 -1 +1-16-16 1 +1-16-17 -1 +1-16-18 -1 +1-16-19 1 +1-16-20 -1 +1-16-21 -1 +1-16-22 1 +1-21-16 1 +1-21-17 -1 +1-21-18 -1 +1-21-19 1 +1-21-20 1 +1-21-21 1 +1-21-22 -1 +1-22-16 -1 +1-22-17 -1 +1-22-18 1 +1-22-19 1 +1-22-20 1 +1-22-21 -1 +1-22-22 -1 +1-27-16 1 +1-27-17 -1 +1-27-18 -1 +1-27-19 -1 +1-27-20 1 +1-27-21 1 +1-27-22 -1 +1-28-16 1 +1-28-17 -1 +1-28-18 -1 +1-28-19 1 +1-28-20 -1 +1-28-21 1 +1-28-22 1 +1-29-16 1 +1-29-17 1 +1-29-18 1 +1-29-19 -1 +1-29-20 -1 +1-29-21 -1 +1-29-22 1 +1-30-16 -1 +1-30-17 -1 +1-30-18 1 +1-30-19 -1 +1-30-20 -1 +1-30-21 -1 +1-30-22 1 +2-3-16 -1 +2-3-17 -1 +2-3-18 -1 +2-3-19 -1 +2-3-20 -1 +2-3-21 -1 +2-3-22 -1 +2-4-16 1 +2-4-17 1 +2-4-18 1 +2-4-19 1 +2-4-20 -1 +2-4-21 1 +2-4-22 -1 +2-5-16 -1 +2-5-17 1 +2-5-18 1 +2-5-19 1 +2-5-20 -1 +2-5-21 -1 +2-5-22 -1 +2-6-16 1 +2-6-17 1 +2-6-18 1 +2-6-19 1 +2-6-20 1 +2-6-21 1 +2-6-22 1 +2-10-16 -1 +2-10-17 -1 +2-10-18 -1 +2-10-19 1 +2-10-20 -1 +2-10-21 1 +2-10-22 -1 +2-11-16 1 +2-11-17 1 +2-11-18 1 +2-11-19 -1 +2-11-20 1 +2-11-21 1 +2-11-22 -1 +2-12-16 1 +2-12-17 -1 +2-12-18 1 +2-12-19 -1 +2-12-20 -1 +2-12-21 -1 +2-12-22 1 +2-13-16 -1 +2-13-17 1 +2-13-18 1 +2-13-19 -1 +2-13-20 1 +2-13-21 -1 +2-13-22 1 +2-18-16 1 +2-18-17 -1 +2-18-18 1 +2-18-19 -1 +2-18-20 -1 +2-18-21 -1 +2-18-22 -1 +2-19-16 1 +2-19-17 -1 +2-19-18 -1 +2-19-19 -1 +2-19-20 1 +2-19-21 -1 +2-19-22 -1 +2-20-16 -1 +2-20-17 1 +2-20-18 1 +2-20-19 1 +2-20-20 1 +2-20-21 1 +2-20-22 -1 +2-24-16 1 +2-24-17 1 +2-24-18 1 +2-24-19 -1 +2-24-20 -1 +2-24-21 1 +2-24-22 -1 +2-25-16 -1 +2-25-17 1 +2-25-18 1 +2-25-19 1 +2-25-20 -1 +2-25-21 -1 +2-25-22 -1 +2-26-16 1 +2-26-17 -1 +2-26-18 1 +2-26-19 -1 +2-26-20 1 +2-26-21 -1 +2-26-22 1 +2-27-16 1 +2-27-17 1 +2-27-18 1 +2-27-19 -1 +2-27-20 1 +2-27-21 -1 +2-27-22 1 diff --git a/2014-group28-PrzybylakHowellsDeng/data/3m/3mshare.csv b/2014-group28-PrzybylakHowellsDeng/data/3m/3mshare.csv new file mode 100644 index 0000000..d1a3b60 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/3m/3mshare.csv @@ -0,0 +1 @@ +Date,Open,High,Low,Close,Volume,Adj Close,Negative,Neutral,Positive 13/01/2014,135.81,137.06,134.57,134.68,2633400,133.8,0,14,1 14/01/2014,135.11,137.41,134.74,137.41,2479700,136.51,263,4304,194 15/01/2014,137.77,138.82,137.56,138.44,3025900,137.54,134,1015,48 16/01/2014,137.74,138.5,137.63,138.16,1792700,137.26,151,1238,210 17/01/2014,137.98,138.75,136.98,137.31,2327900,136.41,,, 18/01/2014,,,,,,,,, 19/01/2014,,,,,,,,, 20/01/2014,,,,,,,180,2331,208 21/01/2014,138.45,138.95,136.3,136.99,2705700,136.1,106,1302,147 22/01/2014,137.35,137.49,136.33,136.48,2118800,135.59,21,124,11 23/01/2014,135.64,135.66,133.95,134.71,2720300,133.83,80,443,66 24/01/2014,133.73,133.73,130.22,130.22,3776100,129.37,,, 25/01/2014,,,,,,,,, 26/01/2014,,,,,,,467,4162,380 27/01/2014,130.02,130.59,128.66,128.96,3312800,128.12,240,1009,185 28/01/2014,129.43,130.01,129.1,129.81,2734200,128.96,271,1038,75 29/01/2014,130.1,131.27,129,130.25,3584000,129.4,94,718,48 30/01/2014,129.96,129.96,126.53,128.05,4102600,127.21,106,633,100 31/01/2014,126.6,129.2,126.42,128.19,3715400,127.35,,, 01/02/2014,,,,,,,,, 02/02/2014,,,,,,,179,639,51 03/02/2014,128.22,128.59,123.61,123.9,4245100,123.09,13,107,17 04/02/2014,126.09,127.64,124.12,126.72,7412500,125.89,266,2515,249 05/02/2014,128.01,128.76,125.92,127.36,4960000,126.53,334,3063,189 06/02/2014,127.6,129.2,127.1,128.9,3828400,128.06,1860,8498,944 07/02/2014,129.57,130.39,128.81,130.33,3263200,129.48,,, 08/02/2014,,,,,,,,, 09/02/2014,,,,,,,83,940,66 10/02/2014,,,,,,,0,8,1 11/02/2014,129.65,130.41,129.02,129.7,3317400,128.85,157,159,51 12/02/2014,129.7,131.49,129.65,130.98,2604000,130.12,105,949,96 13/02/2014,130.34,131,130.01,130.44,2100600,130.44,169,1862,103 14/02/2014,129.29,130.38,128.66,130.14,2850600,130.14,,, 15/02/2014,129.77,132.19,129.5,132.12,3030000,132.12,,, 16/02/2014,,,,,,,,, 17/02/2014,,,,,,,123,1372,133 18/02/2014,,,,,,,657,5373,661 19/02/2014,132.31,132.75,131.64,131.8,2876500,131.8,617,5168,546 20/02/2014,131.33,132.71,130.46,130.56,2719400,130.56,957,6518,1027 21/02/2014,130.65,132.03,130.05,131.56,2155800,131.56,,, 22/02/2014,131.56,132.33,131.3,131.57,2574300,131.57,,, 23/02/2014,,,,,,,314,3351,320 24/02/2014,,,,,,,137,1168,99 25/02/2014,131.89,133.46,131.44,132.2,2454300,132.2,731,1444,155 26/02/2014,132.27,133.43,131.86,132.93,2863100,132.93,175,1106,89 27/02/2014,133.13,133.46,132.28,132.86,2771100,132.86,356,1139,145 28/02/2014,132.63,134.58,132,134.34,3124000,134.34,,, 01/03/2014,134.19,135.2,133.92,134.73,3179400,134.73,,, 02/03/2014,,,,,,,611,1804,159 03/03/2014,133.07,133.81,131.67,132.21,2814400,132.21,,, 04/03/2014,131.92,133.08,131.58,132.68,6975500,132.68,,, 05/03/2014,132.66,134.03,132.19,133.85,3551400,133.85,,, \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/3m/3mtrend.txt b/2014-group28-PrzybylakHowellsDeng/data/3m/3mtrend.txt new file mode 100644 index 0000000..ba1dc29 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/3m/3mtrend.txt @@ -0,0 +1,33 @@ +14/01/2014 1 +15/01/2014 1 +16/01/2014 -1 +17/01/2014 -1 +21/01/2014 -1 +22/01/2014 -1 +23/01/2014 -1 +24/01/2014 -1 +27/01/2014 -1 +28/01/2014 1 +29/01/2014 1 +30/01/2014 -1 +31/01/2014 1 +03/02/2014 -1 +04/02/2014 1 +05/02/2014 1 +06/02/2014 1 +07/02/2014 1 +10/02/2014 -1 +11/02/2014 1 +12/02/2014 -1 +13/02/2014 -1 +14/02/2014 1 +18/02/2014 -1 +19/02/2014 -1 +20/02/2014 1 +21/02/2014 1 +24/02/2014 1 +25/02/2014 1 +26/02/2014 -1 +27/02/2014 1 +28/02/2014 1 +03/03/2014 -1 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/boeing/beoingshare.csv b/2014-group28-PrzybylakHowellsDeng/data/boeing/beoingshare.csv new file mode 100644 index 0000000..a3fe982 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/boeing/beoingshare.csv @@ -0,0 +1 @@ +Date,Open,High,Low,Close,Volume,Adj Close,Negative,Neutral,Positive 13/01/2014,141.55,142.14,140.38,140.7,4462400,139.91,0,14,0 14/01/2014,140.85,141.7,137.8,140.01,8441600,139.22,401,4020,298 15/01/2014,140.3,141.08,140.14,140.62,3030800,139.83,267,1277,140 16/01/2014,140.33,141.45,140.07,140.21,3062900,139.42,35,380,40 17/01/2014,140.08,141,139.75,140.46,3382700,139.67,,, 18/01/2014,,,,,,,,, 19/01/2014,,,,,,,,, 20/01/2014,,,,,,,261,1050,128 21/01/2014,141.46,142.46,140.81,141.67,3240600,140.88,52,302,41 22/01/2014,142.31,144.57,141.87,144.37,4388700,143.56,467,4162,380 23/01/2014,143.1,143.89,141.1,141.31,4491400,140.52,240,1009,185 24/01/2014,140.4,140.47,136.32,136.65,5856800,135.88,,, 25/01/2014,,,,,,,,, 26/01/2014,,,,,,,91,1176,100 27/01/2014,136.7,138.46,135.65,137.36,5057800,136.59,157,672,144 28/01/2014,137.61,138.09,136.44,137.09,4606200,136.32,75,1361,101 29/01/2014,131.7,131.76,128.07,129.78,15993400,129.05,18,314,21 30/01/2014,131.7,131.7,125.2,126.53,10406200,125.82,41,2174,202 31/01/2014,124.46,126.87,123.08,125.26,9732700,124.56,,, 01/02/2014,,,,,,,,, 02/02/2014,,,,,,,0,190,12 03/02/2014,124.24,126.52,122.75,123.08,9309600,122.39,21,560,21 04/02/2014,123.07,123.8,120.53,122.04,9304100,121.36,160,1542,206 05/02/2014,121,121.94,118.77,121.4,9689100,120.72,172,452,87 06/02/2014,121.79,122.72,121.51,122.67,6738800,121.98,184,2371,226 07/02/2014,123.75,127.21,123.65,127.02,8906300,126.31,,, 08/02/2014,,,,,,,,, 09/02/2014,,,,,,,11,190,14 10/02/2014,128.96,128.97,126.35,127.16,8173500,126.45,0,0,0 11/02/2014,127.65,130.69,127.46,130.16,7874000,129.43,10,76,12 12/02/2014,130.29,130.55,128,128.13,5798800,128.13,74,553,53 13/02/2014,127.06,129.94,127.06,129.5,4203400,129.5,18,420,59 14/02/2014,129.09,130.41,128.02,130.16,4807700,130.16,,, 15/02/2014,,,,,,,,, 16/02/2014,,,,,,,,, 17/02/2014,,,,,,,18,1331,17 18/02/2014,130.13,130.94,129.6,130.63,4645300,130.63,86,1738,431 19/02/2014,130.11,130.5,128.37,128.39,5146600,128.39,107,1710,142 20/02/2014,128.48,129.99,127.51,129.56,4466400,129.56,104,1656,165 21/02/2014,129.8,129.8,128.11,128.28,5164000,128.28,,, 22/02/2014,,,,,,,,, 23/02/2014,,,,,,,73,859,99 24/02/2014,128.38,130.8,128.36,129.59,4635700,129.59,15,547,123 25/02/2014,129.3,129.75,126.21,126.78,7308800,126.78,15,302,14 26/02/2014,127.24,127.94,126.36,126.61,4803600,126.61,75,296,51 27/02/2014,126.47,128.56,126.26,128.56,4649700,128.56,344,3306,401 28/02/2014,128.75,129.95,128.06,128.92,4361400,128.92,,, 01/03/2014,,,,,,,32,648,22 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingGrangerCausality.txt b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingGrangerCausality.txt new file mode 100644 index 0000000..6023112 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingGrangerCausality.txt @@ -0,0 +1,20 @@ +Granger Causality +number of lags (no zero) 1 +ssr based F test: F=4.8405 , p=0.0331 , df_denom=44, df_num=1 +ssr based chi2 test: chi2=5.1705 , p=0.0230 , df=1 +likelihood ratio test: chi2=4.9054 , p=0.0268 , df=1 +parameter F test: F=4.8405 , p=0.0331 , df_denom=44, df_num=1 + +Granger Causality +number of lags (no zero) 2 +ssr based F test: F=3.2868 , p=0.0474 , df_denom=41, df_num=2 +ssr based chi2 test: chi2=7.3753 , p=0.0250 , df=2 +likelihood ratio test: chi2=6.8405 , p=0.0327 , df=2 +parameter F test: F=3.2868 , p=0.0474 , df_denom=41, df_num=2 + +Granger Causality +number of lags (no zero) 3 +ssr based F test: F=2.0968 , p=0.1168 , df_denom=38, df_num=3 +ssr based chi2 test: chi2=7.4490 , p=0.0589 , df=3 +likelihood ratio test: chi2=6.8930 , p=0.0754 , df=3 +parameter F test: F=2.0968 , p=0.1168 , df_denom=38, df_num=3 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingcloseprice.txt b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingcloseprice.txt new file mode 100644 index 0000000..e69ae96 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingcloseprice.txt @@ -0,0 +1,37 @@ +3-5 12.56 +3-4 12.51 +3-1 12.52 +2-28 12.54 +2-27 12.48 +2-26 12.32 +2-25 12.25 +2-22 12.41 +2-21 12.36 +2-20 12.48 +2-19 12.65 +2-15 12.63 +2-14 12.66 +2-13 12.68 +2-12 12.63 +2-11 12.63 +2-8 12.66 +2-7 12.66 +2-6 12.64 +2-5 12.63 +2-4 12.53 +2-1 12.71 +1-31 12.64 +1-30 12.63 +1-29 12.63 +1-28 12.63 +1-25 12.57 +1-24 12.51 +1-23 12.5 +1-22 12.47 +1-18 12.48 +1-17 12.45 +1-16 12.32 +1-15 12.39 +1-14 12.43 +1-11 12.45 +1-10 12.46 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingenglishfeatures.txt b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingenglishfeatures.txt new file mode 100644 index 0000000..6a26d4b --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingenglishfeatures.txt @@ -0,0 +1,33 @@ +1-13 0 14 0 +1-14 401 4020 298 +1-15 267 1277 140 +1-16 35 380 40 +1-20 261 1050 128 +1-21 52 302 41 +1-22 467 4162 380 +1-23 240 1009 185 +1-26 91 1176 100 +1-27 157 672 144 +1-28 75 1361 101 +1-29 18 314 21 +1-30 41 2174 202 +2-2 0 190 12 +2-3 21 560 21 +2-4 160 1542 206 +2-5 172 452 87 +2-6 184 2371 226 +2-9 11 180 14 +2-10 0 0 0 +2-11 10 76 12 +2-12 74 553 53 +2-13 18 420 59 +2-17 18 1331 17 +2-18 86 1738 431 +2-19 107 1710 142 +2-20 104 1656 165 +2-23 73 859 99 +2-24 15 547 123 +2-25 15 302 14 +2-26 75 296 51 +2-27 344 3306 401 +3-2 32 648 22 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingfeatures.txt b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingfeatures.txt new file mode 100644 index 0000000..591690d --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingfeatures.txt @@ -0,0 +1,33 @@ +1-13 0 14 0 +1-14 393 4415 319 +1-15 273 1315 117 +1-16 38 390 47 +1-20 248 1138 135 +1-21 48 324 39 +1-22 178 500 67 +1-23 64 473 39 +1-26 97 1215 117 +1-27 163 791 177 +1-28 81 1423 133 +1-29 29 329 30 +1-30 41 2268 208 +2-2 1 196 12 +2-3 24 610 41 +2-4 41 354 39 +2-5 158 491 124 +2-6 209 2521 271 +2-9 10 188 16 +2-10 0 0 0 +2-11 9 82 11 +2-12 78 577 65 +2-13 18 432 53 +2-17 18 1365 22 +2-18 93 1849 438 +2-19 112 1830 193 +2-20 104 1631 172 +2-23 80 851 112 +2-24 16 550 121 +2-25 20 311 19 +2-26 77 327 54 +2-27 339 3290 442 +3-2 33 670 31 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/boeing/boeinghourfeatures.txt b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeinghourfeatures.txt new file mode 100644 index 0000000..ca71314 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeinghourfeatures.txt @@ -0,0 +1,212 @@ +1-13-20 0 14 0 +1-14-15 7 406 15 +1-14-16 12 488 25 +1-14-17 36 756 19 +1-14-18 82 868 140 +1-14-19 168 536 53 +1-14-20 6 332 13 +1-14-21 21 291 13 +1-15-15 4 169 9 +1-15-16 4 135 2 +1-15-17 11 140 13 +1-15-18 3 109 4 +1-15-19 4 317 8 +1-15-20 1 157 6 +1-15-21 6 146 2 +1-16-15 2 100 2 +1-16-16 10 98 10 +1-16-17 4 144 9 +1-16-18 3 88 6 +1-16-19 3 79 0 +1-16-20 2 87 0 +1-16-21 9 102 3 +1-20-15 15 114 13 +1-20-16 8 122 2 +1-20-17 67 119 15 +1-20-18 15 98 11 +1-20-19 22 88 8 +1-20-20 32 97 4 +1-20-21 5 113 11 +1-21-15 3 87 3 +1-21-16 7 595 10 +1-21-17 12 275 8 +1-21-18 0 96 10 +1-21-19 1 65 3 +1-21-20 8 90 7 +1-21-21 6 162 3 +1-22-15 4 122 4 +1-22-16 1 195 2 +1-22-17 3 132 1 +1-22-18 8 131 7 +1-22-19 2 73 6 +1-22-20 4 57 10 +1-22-21 14 169 44 +1-26-15 5 48 17 +1-26-16 3 68 1 +1-26-17 20 48 2 +1-26-18 2 81 7 +1-26-19 0 72 3 +1-26-20 3 57 7 +1-26-21 3 37 9 +1-27-15 13 162 18 +1-27-16 6 101 9 +1-27-17 170 449 6 +1-27-18 4 90 6 +1-27-19 3 68 2 +1-27-20 3 99 2 +1-27-21 8 95 12 +1-28-15 2 47 4 +1-28-16 2 62 5 +1-28-17 5 46 0 +1-28-18 15 75 20 +1-28-19 3 86 3 +1-28-20 14 69 9 +1-28-21 4 86 7 +1-29-15 47 563 101 +1-29-16 104 1030 211 +1-29-17 94 587 58 +1-29-18 43 309 43 +1-29-19 4 568 20 +1-29-20 32 375 30 +1-29-21 45 328 18 +1-30-15 7 167 11 +1-30-16 8 282 9 +1-30-17 8 238 11 +1-30-18 13 371 9 +1-30-19 6 314 13 +1-30-20 39 325 45 +1-30-21 14 601 30 +2-2-15 3 69 13 +2-2-16 0 57 4 +2-2-17 0 61 3 +2-2-18 3 56 4 +2-2-19 5 58 6 +2-2-20 3 51 2 +2-2-21 2 78 15 +2-3-15 12 110 13 +2-3-16 12 89 7 +2-3-17 2 73 2 +2-3-18 7 79 6 +2-3-19 2 75 24 +2-3-20 5 746 4 +2-3-21 11 100 5 +2-4-15 14 87 4 +2-4-16 17 124 34 +2-4-17 9 144 10 +2-4-18 0 107 4 +2-4-19 3 106 21 +2-4-20 17 73 14 +2-4-21 4 92 10 +2-5-15 7 119 15 +2-5-16 9 110 9 +2-5-17 37 135 10 +2-5-18 18 168 5 +2-5-19 7 150 65 +2-5-20 6 335 60 +2-5-21 49 212 62 +2-6-15 44 113 3 +2-6-16 14 172 24 +2-6-17 6 73 27 +2-6-18 16 182 16 +2-6-19 12 120 14 +2-6-20 26 87 15 +2-6-21 4 129 6 +2-9-15 3 41 2 +2-9-16 2 84 5 +2-9-17 2 108 3 +2-9-18 0 58 4 +2-9-19 2 66 3 +2-9-20 3 80 5 +2-9-21 4 89 18 +2-10-15 14 97 7 +2-10-16 153 102 9 +2-10-17 7 423 113 +2-10-18 3 78 11 +2-10-19 3 84 4 +2-10-20 4 111 5 +2-10-21 7 111 40 +2-11-15 2 116 6 +2-11-16 150 288 78 +2-11-17 31 105 16 +2-11-18 11 72 13 +2-11-19 15 111 11 +2-11-20 5 87 3 +2-11-21 6 102 12 +2-12-15 2 62 2 +2-12-16 4 48 2 +2-12-17 3 62 5 +2-12-18 5 62 1 +2-12-19 2 73 7 +2-12-20 1 107 8 +2-12-21 3 52 2 +2-13-15 9 87 3 +2-13-16 0 67 5 +2-13-17 3 57 0 +2-13-18 3 53 1 +2-13-19 2 82 2 +2-13-20 0 41 5 +2-13-21 2 62 5 +2-17-15 3 121 949 +2-17-16 1 87 528 +2-17-17 2 73 146 +2-17-18 11 182 113 +2-17-19 2 164 59 +2-17-20 4 100 56 +2-17-21 1 58 58 +2-18-15 1 137 15 +2-18-16 12 182 16 +2-18-17 9 88 32 +2-18-18 2 104 19 +2-18-19 3 85 14 +2-18-20 4 91 3 +2-18-21 1 78 3 +2-19-15 7 139 5 +2-19-16 2 80 11 +2-19-17 4 59 9 +2-19-18 6 85 14 +2-19-19 1 64 11 +2-19-20 0 59 5 +2-19-21 3 63 2 +2-20-15 16 71 14 +2-20-16 5 70 7 +2-20-17 4 92 3 +2-20-18 1 101 3 +2-20-19 5 77 9 +2-20-20 6 102 8 +2-20-21 1 70 4 +2-23-15 1 30 2 +2-23-16 8 38 6 +2-23-17 4 40 3 +2-23-18 3 46 2 +2-23-19 1 68 9 +2-23-20 9 74 8 +2-23-21 4 41 14 +2-24-15 2 140 10 +2-24-16 5 65 4 +2-24-17 2 65 8 +2-24-18 2 80 4 +2-24-19 2 104 10 +2-24-20 3 74 5 +2-24-21 1 72 9 +2-25-15 6 55 3 +2-25-16 31 90 25 +2-25-17 9 134 5 +2-25-18 1 103 7 +2-25-19 3 127 5 +2-25-20 3 84 8 +2-25-21 21 103 23 +2-26-15 10 118 10 +2-26-16 108 303 43 +2-26-17 81 842 66 +2-26-18 3 173 17 +2-26-19 7 125 12 +2-26-20 20 178 23 +2-26-21 16 253 31 +2-27-15 19 412 57 +2-27-16 24 519 51 +2-27-17 32 396 74 +2-27-18 58 456 73 +2-27-19 78 537 46 +2-27-20 49 375 75 +2-27-21 104 655 66 +3-2-15 6 70 63-2-16 4 72 33-2-17 1 74 03-2-18 15 113 43-2-19 13 101 33-2-20 4 80 33-2-21 5 74 4 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/boeing/boeinghourfeaturesmatched.txt b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeinghourfeaturesmatched.txt new file mode 100644 index 0000000..454cea7 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeinghourfeaturesmatched.txt @@ -0,0 +1,160 @@ +1-15-16 4 135 2 +1-15-17 11 140 13 +1-15-18 3 109 4 +1-15-19 4 317 8 +1-15-20 1 157 6 +1-15-21 6 146 2 +1-16-15 2 100 2 +1-16-16 10 98 10 +1-16-17 4 144 9 +1-16-18 3 88 6 +1-16-19 3 79 0 +1-16-20 2 87 0 +1-16-21 9 102 3 +1-21-15 3 87 3 +1-21-16 7 595 10 +1-21-17 12 275 8 +1-21-18 0 96 10 +1-21-19 1 65 3 +1-21-20 8 90 7 +1-21-21 6 162 3 +1-22-15 4 122 4 +1-22-16 1 195 2 +1-22-17 3 132 1 +1-22-18 8 131 7 +1-22-19 2 73 6 +1-22-20 4 57 10 +1-22-21 14 169 44 +1-27-15 13 162 18 +1-27-16 6 101 9 +1-27-17 170 449 6 +1-27-18 4 90 6 +1-27-19 3 68 2 +1-27-20 3 99 2 +1-27-21 8 95 12 +1-28-15 2 47 4 +1-28-16 2 62 5 +1-28-17 5 46 0 +1-28-18 15 75 20 +1-28-19 3 86 3 +1-28-20 14 69 9 +1-28-21 4 86 7 +1-29-15 47 563 101 +1-29-16 104 1030 211 +1-29-17 94 587 58 +1-29-18 43 309 43 +1-29-19 4 568 20 +1-29-20 32 375 30 +1-29-21 45 328 18 +1-30-15 7 167 11 +1-30-16 8 282 9 +1-30-17 8 238 11 +1-30-18 13 371 9 +1-30-19 6 314 13 +1-30-20 39 325 45 +1-30-21 14 601 30 +2-3-15 12 110 13 +2-3-16 12 89 7 +2-3-17 2 73 2 +2-3-18 7 79 6 +2-3-19 2 75 24 +2-3-20 5 746 4 +2-3-21 11 100 5 +2-4-15 14 87 4 +2-4-16 17 124 34 +2-4-17 9 144 10 +2-4-18 0 107 4 +2-4-19 3 106 21 +2-4-20 17 73 14 +2-4-21 4 92 10 +2-5-15 7 119 15 +2-5-16 9 110 9 +2-5-17 37 135 10 +2-5-18 18 168 5 +2-5-19 7 150 65 +2-5-20 6 335 60 +2-5-21 49 212 62 +2-6-15 44 113 3 +2-6-16 14 172 24 +2-6-17 6 73 27 +2-6-18 16 182 16 +2-6-19 12 120 14 +2-6-20 26 87 15 +2-6-21 4 129 6 +2-10-15 14 97 7 +2-10-16 153 102 9 +2-10-17 7 423 113 +2-10-18 3 78 11 +2-10-19 3 84 4 +2-10-20 4 111 5 +2-10-21 7 111 40 +2-11-15 2 116 6 +2-11-16 150 288 78 +2-11-17 31 105 16 +2-11-18 11 72 13 +2-11-19 15 111 11 +2-11-20 5 87 3 +2-11-21 6 102 12 +2-12-15 2 62 2 +2-12-16 4 48 2 +2-12-17 3 62 5 +2-12-18 5 62 1 +2-12-19 2 73 7 +2-12-20 1 107 8 +2-12-21 3 52 2 +2-13-15 9 87 3 +2-13-16 0 67 5 +2-13-17 3 57 0 +2-13-18 3 53 1 +2-13-19 2 82 2 +2-13-20 0 41 5 +2-13-21 2 62 5 +2-18-15 1 137 15 +2-18-16 12 182 16 +2-18-17 9 88 32 +2-18-18 2 104 19 +2-18-19 3 85 14 +2-18-20 4 91 3 +2-18-21 1 78 3 +2-19-15 7 139 5 +2-19-16 2 80 11 +2-19-17 4 59 9 +2-19-18 6 85 14 +2-19-19 1 64 11 +2-19-20 0 59 5 +2-19-21 3 63 2 +2-20-15 16 71 14 +2-20-16 5 70 7 +2-20-17 4 92 3 +2-20-18 1 101 3 +2-20-19 5 77 9 +2-20-20 6 102 8 +2-20-21 1 70 4 +2-24-15 2 140 10 +2-24-16 5 65 4 +2-24-17 2 65 8 +2-24-18 2 80 4 +2-24-19 2 104 10 +2-24-20 3 74 5 +2-24-21 1 72 9 +2-25-15 6 55 3 +2-25-16 31 90 25 +2-25-17 9 134 5 +2-25-18 1 103 7 +2-25-19 3 127 5 +2-25-20 3 84 8 +2-25-21 21 103 23 +2-26-15 10 118 10 +2-26-16 108 303 43 +2-26-17 81 842 66 +2-26-18 3 173 17 +2-26-19 7 125 12 +2-26-20 20 178 23 +2-26-21 16 253 31 +2-27-15 19 412 57 +2-27-16 24 519 51 +2-27-17 32 396 74 +2-27-18 58 456 73 +2-27-19 78 537 46 +2-27-20 49 375 75 +2-27-21 104 655 66 diff --git a/2014-group28-PrzybylakHowellsDeng/data/boeing/boeinghourtrendmatched.txt b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeinghourtrendmatched.txt new file mode 100644 index 0000000..1c697ab --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeinghourtrendmatched.txt @@ -0,0 +1,160 @@ +1-15-17 1 +1-15-18 -1 +1-15-19 -1 +1-15-20 -1 +1-15-21 1 +1-15-22 -1 +1-16-16 1 +1-16-17 -1 +1-16-18 1 +1-16-19 -1 +1-16-20 -1 +1-16-21 -1 +1-16-22 -1 +1-21-16 1 +1-21-17 -1 +1-21-18 -1 +1-21-19 1 +1-21-20 1 +1-21-21 0 +1-21-22 1 +1-22-16 1 +1-22-17 1 +1-22-18 1 +1-22-19 1 +1-22-20 1 +1-22-21 1 +1-22-22 1 +1-27-16 1 +1-27-17 -1 +1-27-18 -1 +1-27-19 1 +1-27-20 1 +1-27-21 1 +1-27-22 -1 +1-28-16 1 +1-28-17 -1 +1-28-18 -1 +1-28-19 1 +1-28-20 1 +1-28-21 -1 +1-28-22 -1 +1-29-16 -1 +1-29-17 1 +1-29-18 -1 +1-29-19 -1 +1-29-20 1 +1-29-21 -1 +1-29-22 1 +1-30-16 1 +1-30-17 -1 +1-30-18 1 +1-30-19 -1 +1-30-20 -1 +1-30-21 -1 +1-30-22 1 +2-3-16 -1 +2-3-17 -1 +2-3-18 -1 +2-3-19 1 +2-3-20 -1 +2-3-21 -1 +2-3-22 -1 +2-4-16 -1 +2-4-17 -1 +2-4-18 1 +2-4-19 -1 +2-4-20 -1 +2-4-21 -1 +2-4-22 -1 +2-5-16 -1 +2-5-17 1 +2-5-18 1 +2-5-19 1 +2-5-20 1 +2-5-21 -1 +2-5-22 1 +2-6-16 1 +2-6-17 1 +2-6-18 -1 +2-6-19 1 +2-6-20 -1 +2-6-21 1 +2-6-22 1 +2-10-16 1 +2-10-17 -1 +2-10-18 -1 +2-10-19 -1 +2-10-20 -1 +2-10-21 1 +2-10-22 1 +2-11-16 1 +2-11-17 -1 +2-11-18 1 +2-11-19 1 +2-11-20 1 +2-11-21 1 +2-11-22 -1 +2-12-16 1 +2-12-17 -1 +2-12-18 -1 +2-12-19 -1 +2-12-20 1 +2-12-21 -1 +2-12-22 -1 +2-13-16 -1 +2-13-17 1 +2-13-18 1 +2-13-19 1 +2-13-20 1 +2-13-21 1 +2-13-22 -1 +2-18-16 -1 +2-18-17 1 +2-18-18 1 +2-18-19 1 +2-18-20 1 +2-18-21 -1 +2-18-22 1 +2-19-16 -1 +2-19-17 -1 +2-19-18 -1 +2-19-19 -1 +2-19-20 -1 +2-19-21 1 +2-19-22 -1 +2-20-16 -1 +2-20-17 1 +2-20-18 1 +2-20-19 1 +2-20-20 1 +2-20-21 1 +2-20-22 -1 +2-24-16 1 +2-24-17 1 +2-24-18 1 +2-24-19 1 +2-24-20 -1 +2-24-21 -1 +2-24-22 -1 +2-25-16 -1 +2-25-17 1 +2-25-18 1 +2-25-19 -1 +2-25-20 -1 +2-25-21 -1 +2-25-22 -1 +2-26-16 -1 +2-26-17 1 +2-26-18 1 +2-26-19 1 +2-26-20 -1 +2-26-21 -1 +2-26-22 -1 +2-27-16 1 +2-27-17 1 +2-27-18 1 +2-27-19 1 +2-27-20 1 +2-27-21 -1 +2-27-22 1 diff --git a/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingshare.csv b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingshare.csv new file mode 100644 index 0000000..9adcafa --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingshare.csv @@ -0,0 +1 @@ +Date,Open,High,Low,Close,Volume,Adj Close,Negative,Neutral,Positive 13/01/2014,141.55,142.14,140.38,140.7,4462400,139.91,1,12,1 14/01/2014,140.85,141.7,137.8,140.01,8441600,139.22,166,1079,138 15/01/2014,140.3,141.08,140.14,140.62,3030800,139.83,114,615,83 16/01/2014,140.33,141.45,140.07,140.21,3062900,139.42,153,1040,167 17/01/2014,140.08,141,139.75,140.46,3382700,139.67,,, 18/01/2014,,,,,,,,, 19/01/2014,,,,,,,,, 20/01/2014,,,,,,,106,1560,110 21/01/2014,141.46,142.46,140.81,141.67,3240600,140.88,72,1633,93 22/01/2014,142.31,144.57,141.87,144.37,4388700,143.56,134,1357,51 23/01/2014,143.1,143.89,141.1,141.31,4491400,140.52,161,1839,170 24/01/2014,140.4,140.47,136.32,136.65,5856800,135.88,,, 25/01/2014,,,,,,,,, 26/01/2014,,,,,,,364,2806,383 27/01/2014,136.7,138.46,135.65,137.36,5057800,136.59,98,982,92 28/01/2014,137.61,138.09,136.44,137.09,4606200,136.32,288,2555,383 29/01/2014,131.7,131.76,128.07,129.78,15993400,129.05,462,2985,1347 30/01/2014,131.7,131.7,125.2,126.53,10406200,125.82,136,885,114 31/01/2014,124.46,126.87,123.08,125.26,9732700,124.56,,, 01/02/2014,,,,,,,,, 02/02/2014,,,,,,,21,124,11 03/02/2014,124.24,126.52,122.75,123.08,9309600,122.39,80,443,66 04/02/2014,123.07,123.8,120.53,122.04,9304100,121.36,532,3201,302 05/02/2014,121,121.94,118.77,121.4,9689100,120.72,422,2638,207 06/02/2014,121.79,122.72,121.51,122.67,6738800,121.98,2840,7904,874 07/02/2014,123.75,127.21,123.65,127.02,8906300,126.31,,, 08/02/2014,,,,,,,,, 09/02/2014,,,,,,,108,586,53 10/02/2014,128.96,128.97,126.35,127.16,8173500,126.45,0,1,0 11/02/2014,127.65,130.69,127.46,130.16,7874000,129.43,38,141,12 12/02/2014,130.29,130.55,128,128.13,5798800,128.13,94,718,48 13/02/2014,127.06,129.94,127.06,129.5,4203400,129.5,106,633,100 14/02/2014,129.09,130.41,128.02,130.16,4807700,130.16,,, 15/02/2014,,,,,,,,, 16/02/2014,,,,,,,,, 17/02/2014,,,,,,,179,639,51 18/02/2014,130.13,130.94,129.6,130.63,4645300,130.63,266,2515,249 19/02/2014,130.11,130.5,128.37,128.39,5146600,128.39,313,2473,231 20/02/2014,128.48,129.99,127.51,129.56,4466400,129.56,,, 21/02/2014,129.8,129.8,128.11,128.28,5164000,128.28,,, 22/02/2014,,,,,,,,, 23/02/2014,,,,,,,282,2521,191 24/02/2014,128.38,130.8,128.36,129.59,4635700,129.59,100,698,75 25/02/2014,129.3,129.75,126.21,126.78,7308800,126.78,116,824,49 26/02/2014,127.24,127.94,126.36,126.61,4803600,126.61,105,865,103 27/02/2014,126.47,128.56,126.26,128.56,4649700,128.56,92,654,97 28/02/2014,128.75,129.95,128.06,128.92,4361400,128.92,,, \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingshareprice.csv b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingshareprice.csv new file mode 100644 index 0000000..09093ce --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingshareprice.csv @@ -0,0 +1 @@ +Date,Open,High,Low,Close,Volume,Adj Close,Negative,Neutral,Positive 10/01/2013,13.85,13.96,13.83,13.9,376600,12.46,,, 11/01/2013,13.94,13.96,13.85,13.89,228100,12.45,,, 12/01/2013,,,,,,,,, 13/01/2013,,,,,,,,, 14/01/2013,13.89,13.96,13.83,13.87,249900,12.43,,, 15/01/2013,13.85,13.86,13.76,13.82,286600,12.39,,, 16/01/2013,13.76,13.79,13.7,13.75,290600,12.32,,, 17/01/2013,13.81,13.89,13.81,13.89,260600,12.45,,, 18/01/2013,13.85,13.94,13.85,13.93,288500,12.48,,, 19/01/2013,,,,,,,,, 20/01/2013,,,,,,,,, 21/01/2013,,,,,,,,, 22/01/2013,13.9,13.94,13.89,13.91,262500,12.47,,, 23/01/2013,13.88,13.95,13.88,13.95,276200,12.5,,, 24/01/2013,13.95,13.99,13.92,13.96,369800,12.51,,, 25/01/2013,13.97,14.12,13.96,14.02,386000,12.57,,, 26/01/2013,,,,,,,,, 27/01/2013,,,,,,,,, 28/01/2013,14,14.09,13.98,14.09,315900,12.63,,, 29/01/2013,14.05,14.1,14.03,14.09,283400,12.63,,, 30/01/2013,14.15,14.16,14.05,14.09,287300,12.63,,, 31/01/2013,14.06,14.13,14.04,14.1,204700,12.64,,, 01/02/2013,14.19,14.2,14.14,14.18,291900,12.71,,, 02/02/2013,,,,,,,,, 03/02/2013,,,,,,,,, 04/02/2013,14.14,14.14,13.94,13.98,452400,12.53,,, 05/02/2013,14.06,14.11,14.03,14.09,359000,12.63,,, 06/02/2013,14.08,14.14,14.04,14.1,287900,12.64,,, 07/02/2013,14.13,14.14,14.01,14.13,265900,12.66,,, 08/02/2013,14.14,14.17,14.11,14.13,190100,12.66,,, 09/02/2013,,,,,,,,, 10/02/2013,,,,,,,,, 11/02/2013,14.17,14.17,14.06,14.09,227600,12.63,,, 12/02/2013,14.1,14.14,14.05,14.09,260700,12.63,,, 13/02/2013,13.84,13.87,13.8,13.83,292800,12.68,,, 14/02/2013,13.78,13.84,13.77,13.81,286600,12.66,,, 15/02/2013,13.84,13.87,13.72,13.78,244600,12.63,,, 16/02/2013,,,,,,,,, 17/02/2013,,,,,,,,, 18/02/2013,,,,,,,,, 19/02/2013,13.83,13.86,13.74,13.8,374500,12.65,,, 20/02/2013,13.77,13.77,13.6,13.62,555700,12.48,,, 21/02/2013,13.61,13.61,13.42,13.49,382200,12.36,,, 22/02/2013,13.55,13.55,13.48,13.54,255800,12.41,,, 23/02/2013,,,,,,,,, 24/02/2013,,,,,,,,, 25/02/2013,13.56,13.63,13.35,13.37,363100,12.25,,, 26/02/2013,13.42,13.46,13.31,13.44,201800,12.32,,, 27/02/2013,13.45,13.64,13.42,13.62,247100,12.48,,, 28/02/2013,13.67,13.76,13.63,13.68,446600,12.54,,, 01/03/2013,13.66,13.67,13.55,13.66,320600,12.52,,, 02/03/2013,,,,,,,,, 03/03/2013,,,,,,,,, 04/03/2013,13.6,13.66,13.57,13.65,247300,12.51,,, 05/03/2013,13.72,13.78,13.64,13.7,400300,12.56,,, \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingtrend.txt b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingtrend.txt new file mode 100644 index 0000000..23e7c8f --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/boeing/boeingtrend.txt @@ -0,0 +1,33 @@ +2014-01-14 -1 +2014-01-15 1 +2014-01-16 -1 +2014-01-17 1 +2014-01-21 1 +2014-01-22 1 +2014-01-23 -1 +2014-01-24 -1 +2014-01-27 1 +2014-01-28 -1 +2014-01-29 -1 +2014-01-30 -1 +2014-01-31 -1 +2014-02-03 -1 +2014-02-04 -1 +2014-02-05 -1 +2014-02-06 1 +2014-02-07 1 +2014-02-10 1 +2014-02-11 1 +2014-02-12 -1 +2014-02-13 1 +2014-02-14 1 +2014-02-18 1 +2014-02-19 -1 +2014-02-20 1 +2014-02-21 -1 +2014-02-24 1 +2014-02-25 -1 +2014-02-26 -1 +2014-02-27 1 +2014-02-28 1 +2014-03-03 -1 diff --git a/2014-group28-PrzybylakHowellsDeng/data/caterpillar/.DS_Store b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/.DS_Store new file mode 100644 index 0000000..e9ddfc1 Binary files /dev/null and b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/.DS_Store differ diff --git a/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarfeatures.txt b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarfeatures.txt new file mode 100644 index 0000000..998678c --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarfeatures.txt @@ -0,0 +1,33 @@ +1-13 1 12 1 +1-14 156 1077 135 +1-15 119 600 85 +1-16 151 1009 187 +1-20 111 1553 111 +1-21 66 1611 113 +1-22 136 1349 54 +1-23 150 1816 168 +1-26 361 2777 376 +1-27 90 983 83 +1-28 325 2498 337 +1-29 492 2971 1325 +1-30 115 869 108 +2-2 22 124 11 +2-3 84 436 66 +2-4 536 3167 306 +2-5 428 2599 411 +2-6 2809 7805 974 +2-9 106 580 54 +2-10 0 1 0 +2-11 38 140 13 +2-12 89 722 50 +2-13 100 625 105 +2-17 175 640 49 +2-18 269 2468 235 +2-19 313 2432 241 +2-20 420 2740 214 +2-23 281 2486 194 +2-24 122 659 87 +2-25 112 818 53 +2-26 108 837 114 +2-27 96 641 99 +3-2 104 704 65 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourfeatures.txt b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourfeatures.txt new file mode 100644 index 0000000..1760602 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourfeatures.txt @@ -0,0 +1,212 @@ +1-13-20 1 12 1 +1-14-15 13 103 19 +1-14-16 5 81 12 +1-14-17 14 76 6 +1-14-18 13 114 9 +1-14-19 5 70 30 +1-14-20 14 78 9 +1-14-21 41 150 13 +1-15-15 12 79 8 +1-15-16 19 89 11 +1-15-17 16 107 19 +1-15-18 4 90 17 +1-15-19 13 63 8 +1-15-20 18 100 20 +1-15-21 7 127 12 +1-16-15 5 80 5 +1-16-16 29 123 18 +1-16-17 12 62 5 +1-16-18 4 54 10 +1-16-19 4 85 12 +1-16-20 11 94 4 +1-16-21 14 100 21 +1-20-15 7 138 7 +1-20-16 12 157 16 +1-20-17 7 117 11 +1-20-18 8 133 8 +1-20-19 8 72 5 +1-20-20 16 102 8 +1-20-21 9 125 19 +1-21-15 10 88 6 +1-21-16 15 130 9 +1-21-17 27 152 12 +1-21-18 4 91 27 +1-21-19 7 96 3 +1-21-20 5 62 5 +1-21-21 8 126 12 +1-22-15 13 151 7 +1-22-16 8 167 4 +1-22-17 16 159 2 +1-22-18 16 112 11 +1-22-19 13 176 12 +1-22-20 16 155 2 +1-22-21 3 148 10 +1-26-15 15 111 11 +1-26-16 9 95 16 +1-26-17 18 121 15 +1-26-18 24 151 9 +1-26-19 34 124 33 +1-26-20 34 151 68 +1-26-21 18 195 10 +1-27-15 70 351 135 +1-27-16 22 398 49 +1-27-17 30 412 79 +1-27-18 90 266 24 +1-27-19 45 358 23 +1-27-20 66 736 37 +1-27-21 39 319 29 +1-28-15 15 108 21 +1-28-16 22 121 6 +1-28-17 8 125 5 +1-28-18 7 84 9 +1-28-19 8 103 1 +1-28-20 7 85 15 +1-28-21 5 101 23 +1-29-15 21 176 93 +1-29-16 30 186 101 +1-29-17 12 155 84 +1-29-18 21 175 40 +1-29-19 2 137 24 +1-29-20 18 226 46 +1-29-21 31 204 60 +1-30-15 7 186 26 +1-30-16 22 139 29 +1-30-17 20 142 31 +1-30-18 6 130 16 +1-30-19 28 126 18 +1-30-20 8 122 8 +1-30-21 16 1002 26 +2-2-15 8 92 8 +2-2-16 6 128 13 +2-2-17 29 167 11 +2-2-18 46 134 12 +2-2-19 4 88 9 +2-2-20 39 152 24 +2-2-21 5 101 33 +2-3-15 3 58 5 +2-3-16 8 108 8 +2-3-17 10 120 7 +2-3-18 1 51 4 +2-3-19 7 93 4 +2-3-20 6 72 5 +2-3-21 15 125 33 +2-4-15 16 117 4 +2-4-16 16 127 7 +2-4-17 53 124 11 +2-4-18 8 95 2 +2-4-19 23 120 8 +2-4-20 24 143 13 +2-4-21 19 126 20 +2-5-15 22 135 6 +2-5-16 29 128 12 +2-5-17 42 166 10 +2-5-18 10 129 7 +2-5-19 14 222 43 +2-5-20 9 83 31 +2-5-21 12 132 15 +2-6-15 1255 2703 89 +2-6-16 442 874 136 +2-6-17 351 388 79 +2-6-18 112 304 41 +2-6-19 121 352 56 +2-6-20 104 266 152 +2-6-21 58 276 114 +2-9-15 21 95 4 +2-9-16 31 118 7 +2-9-17 25 138 12 +2-9-18 12 110 23 +2-9-19 6 84 8 +2-9-20 16 164 10 +2-9-21 17 115 27 +2-10-15 11 141 9 +2-10-16 17 307 8 +2-10-17 20 270 8 +2-10-18 16 235 13 +2-10-19 5 253 9 +2-10-20 27 254 4 +2-10-21 29 223 8 +2-11-15 31 133 9 +2-11-16 169 235 81 +2-11-17 38 144 23 +2-11-18 46 97 28 +2-11-19 10 141 14 +2-11-20 11 171 34 +2-11-21 21 151 16 +2-12-15 12 99 7 +2-12-16 18 116 9 +2-12-17 9 110 6 +2-12-18 17 164 8 +2-12-19 9 122 13 +2-12-20 7 126 8 +2-12-21 33 101 15 +2-13-15 8 92 13 +2-13-16 6 103 4 +2-13-17 13 113 11 +2-13-18 7 122 10 +2-13-19 21 142 41 +2-13-20 13 122 34 +2-13-21 18 130 9 +2-17-15 10 91 12 +2-17-16 16 126 13 +2-17-17 7 120 5 +2-17-18 17 90 12 +2-17-19 16 112 14 +2-17-20 15 127 23 +2-17-21 35 180 17 +2-18-15 21 66 11 +2-18-16 22 130 14 +2-18-17 13 85 3 +2-18-18 5 125 10 +2-18-19 9 111 11 +2-18-20 12 165 15 +2-18-21 18 133 21 +2-19-15 16 134 8 +2-19-16 5 211 6 +2-19-17 11 106 9 +2-19-18 6 103 19 +2-19-19 13 81 7 +2-19-20 12 109 7 +2-19-21 10 120 9 +2-20-15 35 167 8 +2-20-16 26 112 2 +2-20-17 14 130 3 +2-20-18 8 88 6 +2-20-19 6 131 6 +2-20-20 8 162 3 +2-20-21 23 140 8 +2-23-15 22 98 6 +2-23-16 28 142 19 +2-23-17 11 106 9 +2-23-18 17 128 16 +2-23-19 15 107 6 +2-23-20 21 99 19 +2-23-21 10 76 17 +2-24-15 19 110 14 +2-24-16 16 120 5 +2-24-17 13 102 8 +2-24-18 26 91 8 +2-24-19 19 141 36 +2-24-20 6 124 19 +2-24-21 31 172 31 +2-25-15 8 152 2 +2-25-16 57 228 5 +2-25-17 10 220 8 +2-25-18 14 113 9 +2-25-19 13 201 12 +2-25-20 34 107 47 +2-25-21 17 151 8 +2-26-15 19 148 14 +2-26-16 10 122 5 +2-26-17 16 135 6 +2-26-18 10 109 10 +2-26-19 26 137 18 +2-26-20 18 148 12 +2-26-21 32 132 38 +2-27-15 28 183 12 +2-27-16 52 213 11 +2-27-17 13 114 35 +2-27-18 16 223 27 +2-27-19 168 294 61 +2-27-20 432 1571 358 +2-27-21 134 440 66 +3-2-15 18 99 93-2-16 48 133 103-2-17 18 131 183-2-18 13 125 283-2-19 15 162 123-2-20 30 125 223-2-21 18 212 21 \ No newline at end of file diff --git a/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourfeaturesmatched.txt b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourfeaturesmatched.txt new file mode 100644 index 0000000..d3cac3f --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourfeaturesmatched.txt @@ -0,0 +1,160 @@ +1-15-16 19 89 11 +1-15-17 16 107 19 +1-15-18 4 90 17 +1-15-19 13 63 8 +1-15-20 18 100 20 +1-15-21 7 127 12 +1-16-15 5 80 5 +1-16-16 29 123 18 +1-16-17 12 62 5 +1-16-18 4 54 10 +1-16-19 4 85 12 +1-16-20 11 94 4 +1-16-21 14 100 21 +1-21-15 10 88 6 +1-21-16 15 130 9 +1-21-17 27 152 12 +1-21-18 4 91 27 +1-21-19 7 96 3 +1-21-20 5 62 5 +1-21-21 8 126 12 +1-22-15 13 151 7 +1-22-16 8 167 4 +1-22-17 16 159 2 +1-22-18 16 112 11 +1-22-19 13 176 12 +1-22-20 16 155 2 +1-22-21 3 148 10 +1-27-15 70 351 135 +1-27-16 22 398 49 +1-27-17 30 412 79 +1-27-18 90 266 24 +1-27-19 45 358 23 +1-27-20 66 736 37 +1-27-21 39 319 29 +1-28-15 15 108 21 +1-28-16 22 121 6 +1-28-17 8 125 5 +1-28-18 7 84 9 +1-28-19 8 103 1 +1-28-20 7 85 15 +1-28-21 5 101 23 +1-29-15 21 176 93 +1-29-16 30 186 101 +1-29-17 12 155 84 +1-29-18 21 175 40 +1-29-19 2 137 24 +1-29-20 18 226 46 +1-29-21 31 204 60 +1-30-15 7 186 26 +1-30-16 22 139 29 +1-30-17 20 142 31 +1-30-18 6 130 16 +1-30-19 28 126 18 +1-30-20 8 122 8 +1-30-21 16 1002 26 +2-3-15 3 58 5 +2-3-16 8 108 8 +2-3-17 10 120 7 +2-3-18 1 51 4 +2-3-19 7 93 4 +2-3-20 6 72 5 +2-3-21 15 125 33 +2-4-15 16 117 4 +2-4-16 16 127 7 +2-4-17 53 124 11 +2-4-18 8 95 2 +2-4-19 23 120 8 +2-4-20 24 143 13 +2-4-21 19 126 20 +2-5-15 22 135 6 +2-5-16 29 128 12 +2-5-17 42 166 10 +2-5-18 10 129 7 +2-5-19 14 222 43 +2-5-20 9 83 31 +2-5-21 12 132 15 +2-6-15 1255 2703 89 +2-6-16 442 874 136 +2-6-17 351 388 79 +2-6-18 112 304 41 +2-6-19 121 352 56 +2-6-20 104 266 152 +2-6-21 58 276 114 +2-10-15 11 141 9 +2-10-16 17 307 8 +2-10-17 20 270 8 +2-10-18 16 235 13 +2-10-19 5 253 9 +2-10-20 27 254 4 +2-10-21 29 223 8 +2-11-15 31 133 9 +2-11-16 169 235 81 +2-11-17 38 144 23 +2-11-18 46 97 28 +2-11-19 10 141 14 +2-11-20 11 171 34 +2-11-21 21 151 16 +2-12-15 12 99 7 +2-12-16 18 116 9 +2-12-17 9 110 6 +2-12-18 17 164 8 +2-12-19 9 122 13 +2-12-20 7 126 8 +2-12-21 33 101 15 +2-13-15 8 92 13 +2-13-16 6 103 4 +2-13-17 13 113 11 +2-13-18 7 122 10 +2-13-19 21 142 41 +2-13-20 13 122 34 +2-13-21 18 130 9 +2-18-15 21 66 11 +2-18-16 22 130 14 +2-18-17 13 85 3 +2-18-18 5 125 10 +2-18-19 9 111 11 +2-18-20 12 165 15 +2-18-21 18 133 21 +2-19-15 16 134 8 +2-19-16 5 211 6 +2-19-17 11 106 9 +2-19-18 6 103 19 +2-19-19 13 81 7 +2-19-20 12 109 7 +2-19-21 10 120 9 +2-20-15 35 167 8 +2-20-16 26 112 2 +2-20-17 14 130 3 +2-20-18 8 88 6 +2-20-19 6 131 6 +2-20-20 8 162 3 +2-20-21 23 140 8 +2-24-15 19 110 14 +2-24-16 16 120 5 +2-24-17 13 102 8 +2-24-18 26 91 8 +2-24-19 19 141 36 +2-24-20 6 124 19 +2-24-21 31 172 31 +2-25-15 8 152 2 +2-25-16 57 228 5 +2-25-17 10 220 8 +2-25-18 14 113 9 +2-25-19 13 201 12 +2-25-20 34 107 47 +2-25-21 17 151 8 +2-26-15 19 148 14 +2-26-16 10 122 5 +2-26-17 16 135 6 +2-26-18 10 109 10 +2-26-19 26 137 18 +2-26-20 18 148 12 +2-26-21 32 132 38 +2-27-15 28 183 12 +2-27-16 52 213 11 +2-27-17 13 114 35 +2-27-18 16 223 27 +2-27-19 168 294 61 +2-27-20 432 1571 358 +2-27-21 134 440 66 diff --git a/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourtrend.txt b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourtrend.txt new file mode 100644 index 0000000..1037c68 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourtrend.txt @@ -0,0 +1,426 @@ +1-15-17 1 +1-15-18 1 +1-15-19 -1 +1-15-20 -1 +1-15-21 1 +1-15-22 -1 +1-16-16 1 +1-16-17 -1 +1-16-18 -1 +1-16-19 1 +1-16-20 0 +1-16-21 -1 +1-16-22 1 +1-17-16 1 +1-17-17 1 +1-17-18 1 +1-17-19 -1 +1-17-20 -1 +1-17-21 -1 +1-17-22 -1 +1-21-16 -1 +1-21-17 -1 +1-21-18 -1 +1-21-19 1 +1-21-20 1 +1-21-21 1 +1-21-22 1 +1-22-16 -1 +1-22-17 -1 +1-22-18 -1 +1-22-19 1 +1-22-20 -1 +1-22-21 1 +1-22-22 1 +1-23-16 -1 +1-23-17 0 +1-23-18 -1 +1-23-19 -1 +1-23-20 -1 +1-23-21 1 +1-23-22 -1 +1-24-16 -1 +1-24-17 -1 +1-24-18 1 +1-24-19 -1 +1-24-20 1 +1-24-21 -1 +1-24-22 1 +1-27-16 1 +1-27-17 -1 +1-27-18 -1 +1-27-19 -1 +1-27-20 1 +1-27-21 1 +1-27-22 1 +1-28-16 1 +1-28-17 -1 +1-28-18 -1 +1-28-19 1 +1-28-20 1 +1-28-21 1 +1-28-22 -1 +1-29-16 -1 +1-29-17 -1 +1-29-18 -1 +1-29-19 -1 +1-29-20 0 +1-29-21 -1 +1-29-22 1 +1-30-16 1 +1-30-17 1 +1-30-18 1 +1-30-19 1 +1-30-20 1 +1-30-21 1 +1-30-22 1 +1-31-16 1 +1-31-17 1 +1-31-18 1 +1-31-19 1 +1-31-20 1 +1-31-21 -1 +1-31-22 -1 +2-3-16 -1 +2-3-17 -1 +2-3-18 -1 +2-3-19 1 +2-3-20 -1 +2-3-21 1 +2-3-22 1 +2-4-16 -1 +2-4-17 -1 +2-4-18 1 +2-4-19 1 +2-4-20 -1 +2-4-21 1 +2-4-22 1 +2-5-16 -1 +2-5-17 -1 +2-5-18 1 +2-5-19 -1 +2-5-20 -1 +2-5-21 -1 +2-5-22 1 +2-6-16 1 +2-6-17 1 +2-6-18 -1 +2-6-19 1 +2-6-20 -1 +2-6-21 1 +2-6-22 -1 +2-7-16 1 +2-7-17 1 +2-7-18 1 +2-7-19 1 +2-7-20 1 +2-7-21 -1 +2-7-22 1 +2-10-16 -1 +2-10-17 -1 +2-10-18 1 +2-10-19 1 +2-10-20 1 +2-10-21 1 +2-10-22 -1 +2-11-16 1 +2-11-17 0 +2-11-18 1 +2-11-19 -1 +2-11-20 -1 +2-11-21 1 +2-11-22 -1 +2-12-16 1 +2-12-17 -1 +2-12-18 0 +2-12-19 1 +2-12-20 1 +2-12-21 -1 +2-12-22 -1 +2-13-16 -1 +2-13-17 1 +2-13-18 1 +2-13-19 1 +2-13-20 1 +2-13-21 -1 +2-13-22 -1 +2-14-16 1 +2-14-17 1 +2-14-18 -1 +2-14-19 -1 +2-14-20 1 +2-14-21 1 +2-14-22 -1 +2-18-16 1 +2-18-17 -1 +2-18-18 1 +2-18-19 -1 +2-18-20 -1 +2-18-21 -1 +2-18-22 1 +2-19-16 1 +2-19-17 1 +2-19-18 -1 +2-19-19 1 +2-19-20 -1 +2-19-21 -1 +2-19-22 -1 +2-20-16 -1 +2-20-17 1 +2-20-18 1 +2-20-19 1 +2-20-20 1 +2-20-21 -1 +2-20-22 -1 +2-21-16 1 +2-21-17 -1 +2-21-18 -1 +2-21-19 -1 +2-21-20 1 +2-21-21 1 +2-21-22 -1 +2-24-16 1 +2-24-17 1 +2-24-18 1 +2-24-19 -1 +2-24-20 -1 +2-24-21 -1 +2-24-22 -1 +2-25-16 -1 +2-25-17 1 +2-25-18 1 +2-25-19 1 +2-25-20 1 +2-25-21 -1 +2-25-22 -1 +2-26-16 -1 +2-26-17 1 +2-26-18 -1 +2-26-19 1 +2-26-20 -1 +2-26-21 -1 +2-26-22 -1 +2-27-16 1 +2-27-17 -1 +2-27-18 1 +2-27-19 -1 +2-27-20 1 +2-27-21 -1 +2-27-22 -1 +2-28-16 1 +2-28-17 1 +2-28-18 1 +2-28-19 -1 +2-28-20 1 +2-28-21 -1 +2-28-22 -1 +3-3-16 -1 +3-3-17 -1 +3-3-18 -1 +3-3-19 1 +3-3-20 1 +3-3-21 -1 +3-3-22 1 +3-4-16 1 +3-4-17 1 +3-4-18 -1 +3-4-19 1 +3-4-20 1 +3-4-21 1 +3-4-22 -1 +3-5-16 -1 +3-5-17 -1 +3-5-18 -1 +3-5-19 1 +3-5-20 1 +3-5-21 -1 +3-5-22 1 +3-6-16 1 +3-6-17 1 +3-6-18 1 +3-6-19 1 +3-6-20 -1 +3-6-21 1 +3-6-22 -1 +3-7-16 -1 +3-7-17 1 +3-7-18 -1 +3-7-19 1 +3-7-20 -1 +3-7-21 1 +3-7-22 1 +3-10-15 -1 +3-10-16 -1 +3-10-17 1 +3-10-18 1 +3-10-19 -1 +3-10-20 1 +3-10-21 1 +3-11-15 1 +3-11-16 1 +3-11-17 -1 +3-11-18 1 +3-11-19 0 +3-11-20 -1 +3-11-21 1 +3-12-15 -1 +3-12-16 1 +3-12-17 -1 +3-12-18 1 +3-12-19 -1 +3-12-20 -1 +3-12-21 1 +3-13-15 1 +3-13-16 -1 +3-13-17 1 +3-13-18 -1 +3-13-19 -1 +3-13-20 -1 +3-13-21 1 +3-14-15 -1 +3-14-16 1 +3-14-17 1 +3-14-18 -1 +3-14-19 1 +3-14-20 -1 +3-14-21 1 +3-17-15 1 +3-17-16 -1 +3-17-17 1 +3-17-18 -1 +3-17-19 1 +3-17-20 -1 +3-17-21 -1 +3-18-15 1 +3-18-16 1 +3-18-17 -1 +3-18-18 1 +3-18-19 1 +3-18-20 1 +3-18-21 -1 +3-19-15 1 +3-19-16 -1 +3-19-17 1 +3-19-18 -1 +3-19-19 1 +3-19-20 -1 +3-19-21 -1 +3-20-15 -1 +3-20-16 1 +3-20-17 1 +3-20-18 1 +3-20-19 -1 +3-20-20 1 +3-20-21 1 +3-21-15 1 +3-21-16 1 +3-21-17 -1 +3-21-18 -1 +3-21-19 -1 +3-21-20 1 +3-21-21 -1 +3-24-15 -1 +3-24-16 -1 +3-24-17 -1 +3-24-18 -1 +3-24-19 1 +3-24-20 -1 +3-24-21 -1 +3-25-15 1 +3-25-16 -1 +3-25-17 1 +3-25-18 -1 +3-25-19 1 +3-25-20 -1 +3-25-21 1 +3-26-15 1 +3-26-16 -1 +3-26-17 -1 +3-26-18 1 +3-26-19 -1 +3-26-20 -1 +3-26-21 -1 +3-27-15 1 +3-27-16 1 +3-27-17 1 +3-27-18 1 +3-27-19 -1 +3-27-20 -1 +3-27-21 -1 +3-28-15 1 +3-28-16 -1 +3-28-17 -1 +3-28-18 1 +3-28-19 1 +3-28-20 -1 +3-28-21 1 +3-31-16 1 +3-31-17 -1 +3-31-18 -1 +3-31-19 1 +3-31-20 -1 +3-31-21 1 +3-31-22 -1 +4-1-16 1 +4-1-17 -1 +4-1-18 -1 +4-1-19 0 +4-1-20 1 +4-1-21 -1 +4-1-22 1 +4-2-16 1 +4-2-17 1 +4-2-18 1 +4-2-19 -1 +4-2-20 1 +4-2-21 1 +4-2-22 1 +4-3-16 1 +4-3-17 -1 +4-3-18 1 +4-3-19 1 +4-3-20 -1 +4-3-21 -1 +4-3-22 1 +4-4-16 1 +4-4-17 -1 +4-4-18 -1 +4-4-19 -1 +4-4-20 -1 +4-4-21 -1 +4-4-22 1 +4-7-16 -1 +4-7-17 -1 +4-7-18 -1 +4-7-19 -1 +4-7-20 1 +4-7-21 1 +4-7-22 1 +4-8-16 1 +4-8-17 0 +4-8-18 1 +4-8-19 1 +4-8-20 -1 +4-8-21 -1 +4-8-22 -1 +4-9-16 1 +4-9-17 -1 +4-9-18 1 +4-9-19 1 +4-9-20 -1 +4-9-21 1 +4-9-22 1 +4-10-16 1 +4-10-17 -1 +4-10-18 1 +4-10-19 -1 +4-10-20 1 +4-10-21 -1 +4-10-22 -1 +4-11-16 -1 +4-11-17 1 +4-11-18 -1 +4-11-19 -1 +4-11-20 -1 +4-11-21 1 +4-11-22 -1 diff --git a/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourtrendmatched.txt b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourtrendmatched.txt new file mode 100644 index 0000000..1ea20ff --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillarhourtrendmatched.txt @@ -0,0 +1,160 @@ +1-15-17 1 +1-15-18 1 +1-15-19 -1 +1-15-20 -1 +1-15-21 1 +1-15-22 -1 +1-16-16 1 +1-16-17 -1 +1-16-18 -1 +1-16-19 1 +1-16-20 0 +1-16-21 -1 +1-16-22 1 +1-21-16 -1 +1-21-17 -1 +1-21-18 -1 +1-21-19 1 +1-21-20 1 +1-21-21 1 +1-21-22 1 +1-22-16 -1 +1-22-17 -1 +1-22-18 -1 +1-22-19 1 +1-22-20 -1 +1-22-21 1 +1-22-22 1 +1-27-16 1 +1-27-17 -1 +1-27-18 -1 +1-27-19 -1 +1-27-20 1 +1-27-21 1 +1-27-22 1 +1-28-16 1 +1-28-17 -1 +1-28-18 -1 +1-28-19 1 +1-28-20 1 +1-28-21 1 +1-28-22 -1 +1-29-16 -1 +1-29-17 -1 +1-29-18 -1 +1-29-19 -1 +1-29-20 0 +1-29-21 -1 +1-29-22 1 +1-30-16 1 +1-30-17 1 +1-30-18 1 +1-30-19 1 +1-30-20 1 +1-30-21 1 +1-30-22 1 +2-3-16 -1 +2-3-17 -1 +2-3-18 -1 +2-3-19 1 +2-3-20 -1 +2-3-21 1 +2-3-22 1 +2-4-16 -1 +2-4-17 -1 +2-4-18 1 +2-4-19 1 +2-4-20 -1 +2-4-21 1 +2-4-22 1 +2-5-16 -1 +2-5-17 -1 +2-5-18 1 +2-5-19 -1 +2-5-20 -1 +2-5-21 -1 +2-5-22 1 +2-6-16 1 +2-6-17 1 +2-6-18 -1 +2-6-19 1 +2-6-20 -1 +2-6-21 1 +2-6-22 -1 +2-10-16 -1 +2-10-17 -1 +2-10-18 1 +2-10-19 1 +2-10-20 1 +2-10-21 1 +2-10-22 -1 +2-11-16 1 +2-11-17 0 +2-11-18 1 +2-11-19 -1 +2-11-20 -1 +2-11-21 1 +2-11-22 -1 +2-12-16 1 +2-12-17 -1 +2-12-18 0 +2-12-19 1 +2-12-20 1 +2-12-21 -1 +2-12-22 -1 +2-13-16 -1 +2-13-17 1 +2-13-18 1 +2-13-19 1 +2-13-20 1 +2-13-21 -1 +2-13-22 -1 +2-18-16 1 +2-18-17 -1 +2-18-18 1 +2-18-19 -1 +2-18-20 -1 +2-18-21 -1 +2-18-22 1 +2-19-16 1 +2-19-17 1 +2-19-18 -1 +2-19-19 1 +2-19-20 -1 +2-19-21 -1 +2-19-22 -1 +2-20-16 -1 +2-20-17 1 +2-20-18 1 +2-20-19 1 +2-20-20 1 +2-20-21 -1 +2-20-22 -1 +2-24-16 1 +2-24-17 1 +2-24-18 1 +2-24-19 -1 +2-24-20 -1 +2-24-21 -1 +2-24-22 -1 +2-25-16 -1 +2-25-17 1 +2-25-18 1 +2-25-19 1 +2-25-20 1 +2-25-21 -1 +2-25-22 -1 +2-26-16 -1 +2-26-17 1 +2-26-18 -1 +2-26-19 1 +2-26-20 -1 +2-26-21 -1 +2-26-22 -1 +2-27-16 1 +2-27-17 -1 +2-27-18 1 +2-27-19 -1 +2-27-20 1 +2-27-21 -1 +2-27-22 -1 diff --git a/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillartrend.txt b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillartrend.txt new file mode 100644 index 0000000..a171946 --- /dev/null +++ b/2014-group28-PrzybylakHowellsDeng/data/caterpillar/caterpillartrend.txt @@ -0,0 +1,33 @@ +14/01/2014 1 +15/01/2014 1 +16/01/2014 -1 +17/01/2014 -1 +21/01/2014 -1 +22/01/2014 -1 +23/01/2014 -1 +24/01/2014 -1 +27/01/2014 1 +28/01/2014 1 +29/01/2014 -1 +30/01/2014 1 +31/01/2014 1 +03/02/2014 -1 +04/02/2014 1 +05/02/2014 -1 +06/02/2014 1 +07/02/2014 1 +10/02/2014 -1 +11/02/2014 1 +12/02/2014 1 +13/02/2014 -1 +14/02/2014 1 +18/02/2014 1 +19/02/2014 -1 +20/02/2014 1 +21/02/2014 1 +24/02/2014 -1 +25/02/2014 -1 +26/02/2014 1 +27/02/2014 -1 +28/02/2014 1 +03/03/2014 -1 \ No newline at end of file