Merge branch 'IT17181570' into 'master'

Extract dataset for do the probability distribution questions with dataset

See merge request !62

app/src/main/java/com/elearning/probabilityandstatisticsanalyserandeducator/dataExtraction/ExtractValueForRandomVariable.java

+package com.elearning.probabilityandstatisticsanalyserandeducator.dataExtraction;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Iterator;
+import java.util.List;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+class ExtractValueForRandomVariable {
+    List<String> randomVariable = new ArrayList<String>();
+    List<String> wordlist = new ArrayList<String>();
+    String word;
+    String data;
+
+
+    public List<String> InputRandomVariable(String[] question) {
+
+        int counter = 0;
+        wordlist = Arrays.asList(question);
+        for (String s : question) {
+            word = s.toString().trim();
+            String data1 = word;
+
+
+            Pattern pattern1 = Pattern.compile("\\b(\\d)+(,(\\d)+)*\\b|\\b(\\d)+(\\s(\\d)+)*\\b|\\b(\\d)+(;(\\d)+)*\\b|\\b(\\d)+(:(\\d)+)*\\b");
+            s.replaceAll("\\s","");
+
+            List<Pattern> patterns = new ArrayList<>();
+
+            patterns.add(pattern1);
+
+            for (Pattern pattern : patterns) {
+                Matcher matcher = pattern.matcher(data1);
+
+                while (matcher.find()) {
+                    randomVariable.add(counter, matcher.group().trim());
+                    counter++;
+
+                }
+            }
+
+            Iterator it = randomVariable.iterator();
+            System.out.println("random variable in extract "+ randomVariable.toString());
+            System.out.println("randam variable in extract size"+ randomVariable.size());
+            System.out.println("random variable in extract "+ counter);
+
+        }
+        System.out.println("values: "+data);
+        return randomVariable;
+
+
+    }
+}

app/src/main/java/com/elearning/probabilityandstatisticsanalyserandeducator/dataExtraction/ProbabilityValue.java

+package com.elearning.probabilityandstatisticsanalyserandeducator.dataExtraction;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Iterator;
+import java.util.List;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+class ProbabilityValue {
+    List<String> probabilityvalue = new ArrayList<String>();
+    List<String> wordlist = new ArrayList<String>();
+    String word;
+    String data;
+
+
+    public List<String> ExtractionProbabilityValue(String[] question) {
+
+        int counter = 0;
+        wordlist = Arrays.asList(question);
+        for (String s : question) {
+            word = s.toString().trim();
+            String data1 = word;
+
+
+            Pattern pattern1 = Pattern.compile("\\b(0(\\.\\d+)?|1\\.0)+(,(0(\\.\\d+)?|1\\.0)+)*\\b|\\b(0(\\.\\d+)?|1\\.0)+(\\s(0(\\.\\d+)?|1\\.0)+)*\\b|\\b(0(\\.\\d+)?|1\\.0)+(;(0(\\.\\d+)?|1\\.0)+)*\\b|\\b(0(\\.\\d+)?|1\\.0)+(:(0(\\.\\d+)?|1\\.0)+)*\\b");
+            s.replaceAll("\\s","");
+
+            List<Pattern> patterns = new ArrayList<>();
+
+            patterns.add(pattern1);
+
+            for (Pattern pattern : patterns) {
+                Matcher matcher = pattern.matcher(data1);
+
+                while (matcher.find()) {
+                    probabilityvalue.add(counter, matcher.group().trim());
+                    counter++;
+
+                }
+            }
+
+            Iterator it = probabilityvalue.iterator();
+            System.out.println("probability value in extract "+ probabilityvalue.toString());
+            System.out.println("probability value in extract size"+ probabilityvalue.size());
+            System.out.println("probability value in extract "+ counter);
+
+        }
+        System.out.println("values: "+data);
+        return probabilityvalue;
+
+
+    }
+}

app/src/main/python/probabilitydistribution.py

+from fuzzywuzzy import process
+def main(data,data2):
+	str2match=data
+	stroptions=["A probability distribution of the number of overtime hours worked in one week per employee is listed below.
+				Overtime hours,0,1,2,3,4,5,6
+				Probability,0.016,0.075,0.134,0.31,0.23,0.155,0.08
+				Find the standard deviation of the probability distribution. (Round to 1 decimal place as needed.)"]
+	ratio=process.extract(str2match,data2)
+	highest=process.extractOne(str2match,data2)
+	#print(ratio)
+	check_list=isinstance(data2,list)
+	#print(check_list)
+	#print(type(data2))
+	return ""+str(highest)
\ No newline at end of file

app/src/main/python/probabilitydistribution_keywords.py

+def word2vec(word):
+    from collections import Counter
+    from math import sqrt
+
+    # count the characters in word
+    cw = Counter(word)
+    # precomputes a set of the different characters
+    sw = set(cw)
+    # precomputes the "length" of the word vector
+    lw = sqrt(sum(c*c for c in cw.values()))
+
+    # return a tuple
+    return cw, sw, lw
+
+def cosdis(v1, v2):
+    # which characters are common to the two words?
+    common = v1[1].intersection(v2[1])
+    # by definition of cosine distance we have
+    return sum(v1[0][ch]*v2[0][ch] for ch in common)/v1[2]/v2[2]
+
+def matchkeyword(klist,sen):
+    matchedkeywordlist=[]
+    list_of_keywords = klist
+    Sentence = sen
+    threshold = 0.90
+    for key in list_of_keywords:
+        for word in Sentence.split():
+            try:
+            # print(key)
+               # print(word)
+                res = cosdis(word2vec(word), word2vec(key))
+                #print(res)
+                if res > threshold:
+                    #print("Found a word with cosine distance > 100 : {} with original word: {}".format(word, key))
+                    matchedkeywordlist.append(word)
+            except IndexError:
+                pass
+    return matchedkeywordlist

app/src/main/res/raw/propabilitydistribution.csv

+"The random variable X has a binomial distribution with parameters n=100 and p=0.8. Find the mean and the variance of X."
+"A manufacturing process produces components which are free from any faults with probability p. Find the probability that in a sample of size 50 from a large batch there are fewer than 4 faulty components when p = 0.95. Find the probability that in a sample of size 50 there are fewer than 10 faulty when p = 0.75."
+"Use the table to give a suitable approximation to the probability that 𝑋 ≥ 5 where X is binomial random variable with parameters p = 0.05 and n = 400."
+"Which of the following is not a requirement of a binomial distribution?
+a. Constant probability of success
+b. Only two possible Bernoulli outcomes
+c. Fixed number of trials
+d. Equally likely outcomes"
+"Determine whether the distribution is a discrete probability distribution.
+X 0 1 2 3 4
+P(x) 0.2 0.2 0.2 0.2 0.2"
+"Is the distribution a discrete probability distribution?
+A. No, because each probability is not between 0 and 1, inclusive.
+B. Yes, because the sum of the probabilities is equal to 1 and each probability is between 0 and 1 comma inclusive.
+C. Yes, because the sum of the probabilities is equal to 1.
+D. No, because the sum of the probabilities is not equal to 1"
+"An insurance company sells insurance policies. Each insurance policy leads to claims with an expected value of $100 and a standard deviation of $3,000.The number of policies sold is normally distributed with a mean of 1,000 and a standard deviation of 150.
+(a) What is the expectation of the total of all the claims from policies sold by this company?
+(b) What is the variance of the total of all the claims from this company's policies?"
+"A probability distribution of the number of overtime hours worked in one week per employee is listed below.
+Overtime hours,0,1,2,3,4,5,6
+Probability,0.016,0.075,0.134,0.31,0.23,0.155,0.08
+Find the standard deviation of the probability distribution. (Round to 1 decimal place as needed.)"
+"A probability distribution of the number of overtime hours worked in one week per employee is listed below.
+Overtime hours,0,1,2,3,4,5,6
+Probability,0.016,0.075,0.134,0.31,0.23,0.155,0.08"
+Find the variance of the probability distribution. (Round to 1 decimal place as needed.)"
+"A probability distribution gives us:
+A. A distribution of probabilities
+B. The probability of every possible event in a population
+C. The probability of some of the events in the population
+D. The probability of obtaining certain probabilities"