Merge branch 'IT17181570' into 'master'

Extract keywords from probability distribution essay type questions

See merge request !65

app/build.gradle

@@ -38,7 +38,7 @@ android {
 
         // python.exe file path *********** please change this according to your file path
         python{
-            buildPython "C:/Users/Ruvi/AppData/Local/Programs/Python/Python39/python.exe"
+            buildPython "C:/Users/Cool/AppData/Local/Programs/Python/Python39/python.exe"
         }
     }
 

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

@@ -151,6 +151,74 @@ public class DescriptiveStatisticsQuestionComparation {
 
     }
 
+    /*public List<String> NumberValuesForKeywords(String question) {
+
+        int counting=0;
+        List<String> dataforkeyword = new ArrayList<>();
+
+        List<Pattern> patterns = new ArrayList<>();
+
+
+        //final String example = "1. 21 bricks have a mean mass of 24.2 kg, and 29 similar bricks have a mass of 23.6 kg. Determine the mean mass of the 50 bricks.";
+        String data = question;
+
+        final String regex1 = "mean.*?\\d+(?:,\\d+)*(?:\\d+|(\\.\\d+)?)";
+        final String regex2 = "median.*?\\d+(?:,\\d+)*(?:\\d+|(\\.\\d+)?)";
+        final String regex3 = "mode.*?\\d+(?:,\\d+)*(?:\\d+|(\\.\\d+)?)";
+        final String regex4 = "minimum.*?\\d+(?:,\\d+)*(?:\\d+|(\\.\\d+)?)";
+        final String regex5 = "maximum.*?\\d+(?:,\\d+)*(?:\\d+|(\\.\\d+)?)";
+        final String regex6 = "minimum.*?\\d+(?:,\\d+)*(?:\\d+|(\\.\\d+)?)";
+        final String regex7 = "range.*?\\d+(?:,\\d+)*(?:\\d+|(\\.\\d+)?)";
+        final String regex8 = "first quartile.*?\\d+(?:,\\d+)*(?:\\d+|(\\.\\d+)?)";
+        final String regex9 = "third quartile.*?\\d+(?:,\\d+)*(?:\\d+|(\\.\\d+)?)";
+        final String regex10 = "range.*?\\d+(?:,\\d+)*(?:\\d+|(\\.\\d+)?)";
+        final String regex11 = "inter quartile range.*?\\d+(?:,\\d+)*(?:\\d+|(\\.\\d+)?)";
+
+
+        final Pattern pattern1 = Pattern.compile(regex1, Pattern.MULTILINE);
+        //final Matcher matcher = pattern1.matcher(string);
+
+        final Pattern pattern2 = Pattern.compile(regex2, Pattern.MULTILINE);
+        //final Matcher matcher2 = pattern2.matcher(string);
+
+        final Pattern pattern3 = Pattern.compile(regex3, Pattern.MULTILINE);
+        final Pattern pattern4 = Pattern.compile(regex4, Pattern.MULTILINE);
+        final Pattern pattern5 = Pattern.compile(regex5, Pattern.MULTILINE);
+        final Pattern pattern6 = Pattern.compile(regex6, Pattern.MULTILINE);
+        final Pattern pattern7 = Pattern.compile(regex7, Pattern.MULTILINE);
+        final Pattern pattern8 = Pattern.compile(regex8, Pattern.MULTILINE);
+        final Pattern pattern9 = Pattern.compile(regex9, Pattern.MULTILINE);
+        final Pattern pattern10 = Pattern.compile(regex10, Pattern.MULTILINE);
+        final Pattern pattern11 = Pattern.compile(regex11, Pattern.MULTILINE);
+
+        patterns.add(pattern1);
+        patterns.add(pattern2);
+        patterns.add(pattern3);
+        patterns.add(pattern4);
+        patterns.add(pattern5);
+        patterns.add(pattern6);
+        patterns.add(pattern7);
+        patterns.add(pattern8);
+        patterns.add(pattern9);
+        patterns.add(pattern10);
+        patterns.add(pattern11);
+
+
+        for (Pattern pattern : patterns) {
+            Matcher matcher = pattern.matcher(data);
+            //System.out.println("before matcher loop" + pattern.toString());
+            while (matcher.find()) {
+                System.out.println("Full match: " + matcher.group(0));
+                for (int i = 1; i <= matcher.groupCount(); i++) {
+                    System.out.println("Group " + i + ": " + matcher.group(i));
+                    dataforkeyword.add(counting, matcher.group().trim());
+                    counting++;
+                }
+            }
+        }
+        return dataforkeyword;
+    }*/
+
 
 
 

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

@@ -7,7 +7,7 @@ import java.util.List;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
-class ExtractValueForRandomVariable {
+public class ExtractValueForRandomVariable {
     List<String> randomVariable = new ArrayList<String>();
     List<String> wordlist = new ArrayList<String>();
     String word;

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

+package com.elearning.probabilityandstatisticsanalyserandeducator.dataExtraction;
+
+import android.util.Log;
+
+import com.chaquo.python.PyObject;
+import com.chaquo.python.Python;
+import com.elearning.probabilityandstatisticsanalyserandeducator.R;
+import com.elearning.probabilityandstatisticsanalyserandeducator.inputMethod.DescriptiveSCinputMethod;
+import com.elearning.probabilityandstatisticsanalyserandeducator.inputMethod.ProbabilityDistributionsIM;
+
+import org.w3c.dom.ls.LSOutput;
+
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.nio.charset.Charset;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+public class ProbabilityDistributionQuestionComparation {
+    Python py=null;
+    ProbabilityDistributionsIM probabilityDistributionsIM;
+
+    String a="Let X and Y be two independent random variables. Suppose that we know Var(2X−Y)=6 and Var(X+2Y)=9. Find Var(X) and Var(Y).";
+
+
+    public String ProbabilityDistributionComparewithCSV(String Probabilitydistributionquestions, List<String> reading) {
+
+        // System.out.println("reading des questions in dsqc "+reading);
+
+
+        String[] keywordlist = {"Probability","probability","Distribution","distribution","Random","random","Variable","variable","Normal","normal","Exponential","exponential","Element","element","Discrete","discrete","Function","function","P(X = x)̄","ΣP(x)=1","mass","Mass","cumulative","Cumulative","F(x)","P(X≤x)","mean","Mean","Expected","Value","expected","value","E(X)","Variance","variance","var(X)","V(X)","Standard","standard","Deviation","deviation","σ","μ"};
+        String b="A probability distribution of the number of overtime hours worked in one week per employee is listed below.\n" +
+                "Overtime hours,0,1,2,3,4,5,6\n" +
+                "Probability,0.016,0.075,0.134,0.31,0.23,0.155,0.08\n" +
+                "Find the standard deviation of the probability distribution. (Round to 1 decimal place as needed.)";
+        //System.out.println("String b:" + b);
+
+        List<String> questions ;
+        List<String> matchprodiskeyword = new ArrayList<>();
+
+        questions= reading;
+        String[] dataReader = new String[questions.size()];
+        questions.toArray(dataReader);
+        for (int i=0; i<dataReader.length; i++){
+
+        }
+
+        String questionlist = "";
+        for (String s : questions){
+            questionlist += s + "\t";
+        }
+
+
+        py = Python.getInstance();
+        PyObject pyo = py.getModule("probabilitydistribution");
+        PyObject pyo1 = py.getModule("probabilitydistribution_keywords");
+
+        PyObject obj = pyo.callAttr("main",a,dataReader);
+        PyObject obj1 = pyo1.callAttr("matchkeyword",keywordlist,Probabilitydistributionquestions);
+
+        String result=obj.toString();
+        String result1=obj1.toString();
+
+         System.out.println("output matching: "+result);
+         System.out.println("matching: "+result1);
+        matchprodiskeyword = QuestionMatch(result);
+
+        return result;
+
+    }
+
+
+
+    private List<String> readProbDistributionQuestions(InputStream in){
+        String[] printQuestion = new String[500];
+        List<ProbabiltyDistributionCSVfile> probDistributionQuestions= new ArrayList<>();
+        List<String> StringprobdistributionQuestions= new ArrayList<>();
+        //InputStream is = getResources().openRawResource(R.raw.propabilitydistribution);
+
+        BufferedReader reader = new BufferedReader(
+                new InputStreamReader(in, Charset.forName("UTF-8"))
+        );
+
+
+
+        String line = "";
+        try {
+
+            while ((line = reader.readLine()) != null) {
+                //Split by '"'
+                String tokens = line;
+
+                //Read the csv
+                ProbabiltyDistributionCSVfile question = new ProbabiltyDistributionCSVfile();
+                question.setQuestion(tokens);
+                probDistributionQuestions.add(question);
+                StringprobdistributionQuestions.add(tokens);
+                //printQuestion[lines] = line;
+
+               // Log.d("MyActivity", "Just created: " + question);
+            }
+        } catch (IOException e) {
+            //Log.wtf("MyActivity", "Error reading data file on line " + line, e);
+            e.printStackTrace();
+        }
+        finally {
+            try {
+                reader.close();
+            }catch (IOException e) {
+                e.printStackTrace();
+            }
+        }
+
+        return StringprobdistributionQuestions;
+    }
+
+
+    String data;
+
+    public List<String> QuestionMatch(String highest) {
+
+        int counter = 0;
+        List<String> wordlist = new ArrayList<String>();
+        List<String> matchword = new ArrayList<String>();
+        List<String> valueAccordingtoLine = new ArrayList<>();
+        String word;
+
+        return valueAccordingtoLine;
+
+    }
+
+    public List<String> ExtractDatasetFromDistributionQuestion(String question) {
+
+        List<String> extractnumbervalues = new ArrayList<String>();
+
+
+        Pattern pattern1 = Pattern.compile("(?<=\\s)\\d++(?!\\.\\b)");
+        Matcher matcher1 = pattern1.matcher(question);
+        boolean value1 = matcher1.matches();
+
+
+        while (matcher1.find()) {
+            System.out.println("'" + matcher1.group().trim() + "'");
+            extractnumbervalues.add(matcher1.group().trim());
+        }
+
+        //System.out.println("matched data set of extract " + extractnumbervalues);
+
+        return extractnumbervalues;
+
+    }
+
+}

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

@@ -7,7 +7,7 @@ import java.util.List;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
-class ProbabilityValue {
+public class ProbabilityValue {
     List<String> probabilityvalue = new ArrayList<String>();
     List<String> wordlist = new ArrayList<String>();
     String word;

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

+package com.elearning.probabilityandstatisticsanalyserandeducator.dataExtraction;
+
+public class ProbabiltyDistributionCSVfile {
+    private String question;
+
+    public String getQuestion() {
+        return question;
+    }
+
+    public void setQuestion(String question) {
+        this.question = question;
+    }
+}

app/src/main/java/com/elearning/probabilityandstatisticsanalyserandeducator/inputMethod/DescriptiveSCinputMethod.java

@@ -54,6 +54,7 @@ import java.io.OutputStream;
 import java.nio.charset.Charset;
 import java.util.ArrayList;
 import java.util.Arrays;
+import java.util.HashSet;
 import java.util.List;
 
 
@@ -316,8 +317,10 @@ public class DescriptiveSCinputMethod extends AppCompatActivity {
                     DescriptiveStatisticsQuestionComparation dsqc = new DescriptiveStatisticsQuestionComparation();
                     List<String> reading = readDesQuestions();
                     List<String> extractDatasetForEssay;
+                    List<String> extractNumbervalue;
                     String[] extractDatasetForEssayArray = new String[0];
 
+
                     String extractedKeywordsFromFuzzy = null;
 
                     if (selectedType.equals("Solve Essay problem")) {
@@ -327,8 +330,13 @@ public class DescriptiveSCinputMethod extends AppCompatActivity {
                         //--------------------extrct dataset from DescripticeStatsQuesCompare class using ExtractDatasetfromDescriptiveQuestion method -----------------------------
 
                         extractDatasetForEssay = dsqc.ExtractDatasetFromDescriptiveQuestion(output);
+
+
                         System.out.println("extractDatasetForEssay " + extractDatasetForEssay);
+                        //System.out.println("extractNumbervalue " + extractNumbervalue);
+                       // System.out.println("words by words " + str.toString());
 
+                        //System.out.println("Common elements == "+common);
                         // Converting list to array after data extraction function
                         extractDatasetForEssayArray = new String[extractDatasetForEssay.size()];
                         extractDatasetForEssayArray = extractDatasetForEssay.toArray(extractDatasetForEssayArray);

app/src/main/java/com/elearning/probabilityandstatisticsanalyserandeducator/inputMethod/ProbabilityDistributionsIM.java

@@ -40,6 +40,10 @@ import com.elearning.probabilityandstatisticsanalyserandeducator.calculationfunc
 import com.elearning.probabilityandstatisticsanalyserandeducator.dataExtraction.DescriptiveStatisticsCSVfile;
 import com.elearning.probabilityandstatisticsanalyserandeducator.dataExtraction.DescriptiveStatisticsQuestionComparation;
 import com.elearning.probabilityandstatisticsanalyserandeducator.dataExtraction.ExtractData;
+import com.elearning.probabilityandstatisticsanalyserandeducator.dataExtraction.ExtractValueForRandomVariable;
+import com.elearning.probabilityandstatisticsanalyserandeducator.dataExtraction.ProbabilityDistributionQuestionComparation;
+import com.elearning.probabilityandstatisticsanalyserandeducator.dataExtraction.ProbabilityValue;
+import com.elearning.probabilityandstatisticsanalyserandeducator.dataExtraction.ProbabiltyDistributionCSVfile;
 import com.google.android.material.floatingactionbutton.FloatingActionButton;
 import com.googlecode.tesseract.android.TessBaseAPI;
 import com.theartofdev.edmodo.cropper.CropImage;
@@ -71,7 +75,8 @@ public class ProbabilityDistributionsIM extends AppCompatActivity {
 
     Python py = null;
 
-    List<String> extractedData;
+    List<String> extractedData1;
+    List<String> extractedData2;
     Integer[] valuesTakenFromEditTextArray;
 
     // ImageView imageView, img_greyview;
@@ -83,7 +88,9 @@ public class ProbabilityDistributionsIM extends AppCompatActivity {
 
 
     //ExtractData class Instance
-    ExtractData extractData;
+    //ExtractData extractData;
+    ExtractValueForRandomVariable extractValueForRandomVariable;
+    ProbabilityValue probabilityValue;
 
     Uri uri;
 
@@ -128,12 +135,14 @@ public class ProbabilityDistributionsIM extends AppCompatActivity {
         setImageProperties = new SetImageProperties();
 
         // Arraylist to pass the data
-        extractedData = new ArrayList<>();
+        extractedData1 = new ArrayList<>();
+        extractedData2 = new ArrayList<>();
 
         valuesTakenFromEditTextArray = new Integer[]{};
 
         // initializing the object of ExtractData class
-        extractData = new ExtractData();
+        extractValueForRandomVariable = new ExtractValueForRandomVariable();
+        probabilityValue = new ProbabilityValue();
 
         //intitalzing the OCR object
         ocr = new OCR();
@@ -324,36 +333,50 @@ public class ProbabilityDistributionsIM extends AppCompatActivity {
 
                     // -------------**** getting the final input from edit text
                     String output = textInput.getText().toString().trim();
+                    String output1 = textInput_2.getText().toString().trim();
 
-                    if (extractedData.size() == 0) {
-                        extractedData.add(output); // adding data to List
+                    if (extractedData1.size() == 0) {
+                        extractedData1.add(output); // adding data to List
                     }
 
-                    System.out.println("ExctractedData list size " + extractedData.size());
+                    System.out.println("ExctractedData list size " + extractedData1.size());
 
                     // adding List  to array in order to pass to ExtractData function
-                    String[] dataArray = new String[extractedData.size()];
-                    dataArray = extractedData.toArray(dataArray);
+                    String[] dataArray1 = new String[extractedData1.size()];
+                    dataArray1 = extractedData1.toArray(dataArray1);
 
+                    if (extractedData2.size() == 0) {
+                        extractedData2.add(output1); // adding data to List
+                    }
+
+                    System.out.println("ExctractedData1 list size " + extractedData2.size());
+
+                    // adding List  to array in order to pass to ExtractData function
+                    String[] dataArray2 = new String[extractedData2.size()];
+                    dataArray2 = extractedData2.toArray(dataArray2);
 
+// --------------------------------- Use ProbabilityDistributionQuestionComparation class methods for solve essay type question --------------------------
                     //list to receive the extrated data
                     List<String> extractedDataset;
+                    List<String> extractedDataset1;
 
-
-                    DescriptiveStatisticsQuestionComparation dsqc = new DescriptiveStatisticsQuestionComparation();
-                    List<String> reading = readDesQuestions();
+                    ProbabilityDistributionQuestionComparation pdqc = new ProbabilityDistributionQuestionComparation();
+                    List<String> reading = readProbDistributionQuestions();
                     List<String> extractDatasetForEssay;
                     String[] extractDatasetForEssayArray = new String[0];
 
                     String extractedKeywordsFromFuzzy = null;
 
+
+
+
                     if (selectedType.equals("Solve Essay problem")) {
 
-                        extractedKeywordsFromFuzzy = dsqc.DescriptiveStatisticsQuestionComparewithCSV(output, reading);
+                        extractedKeywordsFromFuzzy = pdqc.ProbabilityDistributionComparewithCSV(output, reading);
                         System.out.println("extractedKeywordsFromFuzzy " + extractedKeywordsFromFuzzy);
                         //--------------------extrct dataset from DescripticeStatsQuesCompare class using ExtractDatasetfromDescriptiveQuestion method -----------------------------
 
-                        extractDatasetForEssay = dsqc.ExtractDatasetFromDescriptiveQuestion(output);
+                        extractDatasetForEssay = pdqc.ExtractDatasetFromDistributionQuestion(output);
                         System.out.println("extractDatasetForEssay " + extractDatasetForEssay);
 
                         // Converting list to array after data extraction function
@@ -363,7 +386,8 @@ public class ProbabilityDistributionsIM extends AppCompatActivity {
                     }
 
                     //calling the extract data function for normal question solvings
-                    extractedDataset = extractData.ExtractionWithComma(dataArray);
+                    extractedDataset = extractValueForRandomVariable.InputRandomVariable(dataArray1);
+                    extractedDataset1 = probabilityValue.ExtractionProbabilityValue(dataArray2);
 
 
                     //-------------------------------------------------------------------------------------------------------------------------------- remove lateer
@@ -373,6 +397,9 @@ public class ProbabilityDistributionsIM extends AppCompatActivity {
                     String[] datasetArray = new String[extractedDataset.size()];
                     datasetArray = extractedDataset.toArray(datasetArray);
 
+                    String[] datasetArray1 = new String[extractedDataset1.size()];
+                    datasetArray1 = extractedDataset1.toArray(datasetArray1);
+
 
                     // System.out.println("selected Type "+selectedRadioButton.getText().toString());
 
@@ -387,7 +414,9 @@ public class ProbabilityDistributionsIM extends AppCompatActivity {
                     }
 
                     extractedDataset.clear();
+                    extractedDataset1.clear();
                     datasetArray = null;
+                    datasetArray1 = null;
                     startActivity(intent);
 
                 }
@@ -638,4 +667,48 @@ public class ProbabilityDistributionsIM extends AppCompatActivity {
         return StringdescriptiveQuestions;
     }
 
+    //----------------------readProbDistributionQuestion method from ProbabilityDistributionQuestionComparation class-----------------------------------------------------------------------
+    private List<String> readProbDistributionQuestions(){
+        String[] printQuestion = new String[500];
+        List<ProbabiltyDistributionCSVfile> probDistributionQuestions= new ArrayList<>();
+        List<String> StringprobdistributionQuestions= new ArrayList<>();
+        InputStream is = getResources().openRawResource(R.raw.propabilitydistribution);
+        BufferedReader reader = new BufferedReader(
+                new InputStreamReader(is, Charset.forName("UTF-8"))
+        );
+
+
+
+        String line = "";
+        try {
+
+            while ((line = reader.readLine()) != null) {
+                //Split by '"'
+                String tokens = line;
+
+                //Read the csv
+                ProbabiltyDistributionCSVfile question = new ProbabiltyDistributionCSVfile();
+                question.setQuestion(tokens);
+                probDistributionQuestions.add(question);
+                StringprobdistributionQuestions.add(tokens);
+                //printQuestion[lines] = line;
+
+                //Log.d("MyActivity", "Just created: " + question);
+            }
+        } catch (IOException e) {
+             //Log.wtf("MyActivity", "Error reading data file on line " + line, e);
+            e.printStackTrace();
+        }
+        finally {
+            try {
+                reader.close();
+            }catch (IOException e) {
+                e.printStackTrace();
+            }
+        }
+
+        return StringprobdistributionQuestions;
+    }
+
+
 }
\ No newline at end of file

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.)"]
+	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)