public override void Map(string inputLine, MapperContext context)
{
char[] delimiterChars = { ',' };
//split up the passed in line
string[] individualItems = inputLine.Trim().Split(delimiterChars);
//Step to Identify the Practice or Prescription data set
//Using the SDK, tried to use the MapperContext.InputFileName property: it is always empty
//So decided to use items count of each datasets
//Items count 8 for practice and Items count 9 for prescription
if (individualItems.Count() == 8)
{
Practices practice = practiceLinereader.ExtractPracticesFromCsvLineFormat(inputLine);
if (String.IsNullOrWhiteSpace(practice.ReferenceId))
{
return;
} //Ignore, practise name cannot be null
if (String.IsNullOrWhiteSpace(practice.Name))
{
return;
} //Ignore, practise name cannot be null
if (String.IsNullOrWhiteSpace(practice.PostCode))
{
return;
} //Ignore, practise name cannot be null
context.EmitKeyValue(practice.ReferenceId, Convert.ToString(practice.PostCode));
}
//Items count 9 for prescription
if (individualItems.Count() == 9)
{
Prescription prescription = prescriptionLinereader.ExtractPrescriptionsFromCsvLineFormat(inputLine);
if (String.IsNullOrWhiteSpace(prescription.PracticeId))
{
return;
} //Ignore, practise name cannot be null
// parctice Id with Amount
context.EmitKeyValue(prescription.PracticeId, prescription.ActualCost.ToString("0.00"));
}
}
public override void Map(string inputLine, MapperContext context)
{
List <string> split_input;
// Replace '- ' with empty value, so input lines are separated only by white space
inputLine = inputLine.Replace("- ", "");
// Using Regex to split input lines by white space unless text enclosed with in double quotes and '[]' and store each field as list
split_input = System.Text.RegularExpressions.Regex.Matches(inputLine, @"[\""].+?[\""]|[[].+?[]]|[^ ]+")
.Cast <System.Text.RegularExpressions.Match>()
.Select(m => m.Value)
.ToList();
string val = string.Empty;
// Record without host name and Date are not taken into consideration
if (split_input.Count > 1)
{
// Parsing date string to DateTime format with date alone, excluding time
DateTime date = DateTime.Parse(split_input[1].Substring(1, split_input[1].IndexOf(':') - 1));
foreach (string s in split_input)
{
val += s + "\t";
}
if (!string.IsNullOrEmpty(split_input[4]))
{
context.EmitKeyValue(split_input[0] + "\t", val);
}
}
}
public override void Map(string inputLine, MapperContext context)
{
var delivery = new Delivery();
double result = 0.0;
context.Log("MAPPER:::START");
context.Log(inputLine);
context.Log("UTF-8: " + Encoding.UTF8.GetBytes(inputLine).Length);
context.Log("ASCII: " + Encoding.ASCII.GetBytes(inputLine).Length);
// Read the incoming string as a Thrift Binary serialized object
var inputStream = new MemoryStream(Encoding.UTF8.GetBytes(inputLine));
using (var transport = new TStreamTransport(inputStream, null))
{
delivery.Read(new TBinaryProtocol(transport));
context.Log("MAPPER:::AFTER_READ");
// Get the driven kilometers from the vehicle's odometer sensor
var sensorData = delivery.Vehicle.SensorHistory;
var minOdo = sensorData.Min(d => d.OdoMeter);
var maxOdo = sensorData.Max(d => d.OdoMeter);
result = maxOdo - minOdo;
context.Log("MAPPER:::BEFORE_STREAM_CLOSE");
}
context.Log("MAPPER:::AFTER_STREAM_CLOSE");
// Emit the vehicle id, and the driven kilometers.
if (result > 0.1)
{
context.EmitKeyValue(delivery.Vehicle.VehicleId, result.ToString(CultureInfo.InvariantCulture));
}
context.Log("MAPPER:::END");
}
public override void Map(string inputLine, MapperContext context)
{
try
{
var doc = XDocument.Parse(inputLine);
var sensors =
doc.Descendants("sensor")
.Select(
element => new
{
name = (string)element.Attribute("name"),
value = element.Value
});
foreach (var sensor in sensors)
{
context.EmitKeyValue(sensor.name, sensor.value);
}
}
catch (Exception x)
{
context.EmitLine(x.ToString());
}
}
// Gets the total number of purchases made by users in North America & in Europe.
// The input is the output from the AggregatePurchaseMapper job (which map reduced the 'clickstearm' data file).
// In format........'Country \t Number of Purchases \t % of the purchases made by New users'
// E.g. 'France 5 20'
public override void Map(string inputLine, MapperContext context)
{
var dataRow = inputLine.Split('\t');
if (dataRow.Count() == 3)
{
var country = dataRow[0];
int numPurchases;
int percentNew;
if (int.TryParse(dataRow[1], out numPurchases) && int.TryParse(dataRow[2], out percentNew))
{
var continent = string.Empty;
if (_europeanCountries.Contains(country))
{
continent = "Europe";
}
else if (_northAmericanCountries.Contains(country))
{
continent = "North America";
}
if (!string.IsNullOrEmpty(continent))
{
var numNewUserPurchases = numPurchases * percentNew / 100;
context.EmitKeyValue(continent, numNewUserPurchases.ToString(CultureInfo.InvariantCulture));
}
}
}
}
public override void Map(string inputLine, MapperContext context)
{
Console.WriteLine("inputLine" + inputLine);
var words = inputLine.Split(new char[] { ' ' }).ToList();
words.ForEach((word) => context.EmitKeyValue(word, "1"));
}
// Gets the total number of purchases made by users in North America & in Europe.
// The input is the output from the AggregatePurchaseMapper job (which map reduced the 'clickstearm' data file).
// In format........'Country \t Number of Purchases \t % of the purchases made by New users'
// E.g. 'France 5 20'
public override void Map(string inputLine, MapperContext context)
{
var dataRow = inputLine.Split('\t');
if (dataRow.Count() == 3)
{
var country = dataRow[0];
int numPurchases;
int percentNew;
if (int.TryParse(dataRow[1], out numPurchases) && int.TryParse(dataRow[2], out percentNew))
{
var continent = string.Empty;
if (_europeanCountries.Contains(country))
{
continent = "Europe";
}
else if (_northAmericanCountries.Contains(country))
{
continent = "North America";
}
if (!string.IsNullOrEmpty(continent))
{
var numNewUserPurchases = numPurchases * percentNew / 100;
context.EmitKeyValue(continent, numNewUserPurchases.ToString(CultureInfo.InvariantCulture));
}
}
}
}
public override void Map(string inputLine, MapperContext context)
{
var data = inputLine.Split('\t');
//countrycode --- name,value,originalValue
context.EmitKeyValue(data[0], data[1] + '\t' + data[2] + '\t' + data[3] + '\t' + data[4]);
}
public override void Map(string inputLine, MapperContext context)
{
string key;
// Replace '- ' with empty value, so input lines are separated only by white space
inputLine = inputLine.Replace("- ", "");
List <string> line_fields;
// Using Regex to split input lines by white space unless text enclosed with in double quotes and '[]' and store each field as list
line_fields = System.Text.RegularExpressions.Regex.Matches(inputLine, @"[\""].+?[\""]|[[].+?[]]|[^ ]+")
.Cast <System.Text.RegularExpressions.Match>()
.Select(m => m.Value)
.ToList();
inputLine = string.Empty;
//Remove all special characters in Byte column
line_fields[4] = System.Text.RegularExpressions.Regex.Replace(line_fields[4], "[^0-9_]+", "").Trim(' ');
//Set '0' if string contain empty space
if (string.IsNullOrEmpty(line_fields[4]))
{
line_fields[4] = "0";
}
//Split the each column by '\t' tab seperator.
foreach (string s in line_fields)
{
inputLine += s + "\t";
}
inputLine = inputLine.TrimEnd('\t');
//Set Hostname as Key for filtering
key = line_fields[0];
context.EmitKeyValue(key, inputLine.ToString());
}
public override void Map(string inputLine, MapperContext context)
{
List <string> split_input;
// Replace '- ' with empty value, so input lines are separated only by white space
inputLine = inputLine.Replace("- ", "");
// Using Regex to split input lines by white space unless text enclosed with in double quotes and '[]' and store each field as list
split_input = System.Text.RegularExpressions.Regex.Matches(inputLine, @"[\""].+?[\""]|[[].+?[]]|[^ ]+")
.Cast <System.Text.RegularExpressions.Match>()
.Select(m => m.Value)
.ToList();
string val = string.Empty;
if (split_input.Count > 1)
{
// Each column in record separated by \t
foreach (string s in split_input)
{
val += s + "\t";
}
// Emitting column 2 as key with entire row.
context.EmitKeyValue(split_input[1], val);
}
}
public override void Map(string inputLine, MapperContext context)
{
//Step to Identify the Practice or Prescription data set
//Using the SDK, tried to use the MapperContext.InputFileName property: it is always empty
//So decided to use items count of each datasets
//Items count 8 for practice and Items count 9 for prescription
char[] delimiterChars = { ',' };
//split up the passed in line
string[] individualItems = inputLine.Trim().Split(delimiterChars);
if (individualItems.Count() == 9)
{
Prescription prescription = reader.ExtractPrescriptionsFromCsvLineFormat(inputLine);
if (String.IsNullOrWhiteSpace(prescription.PracticeId))
{
return;
} //Ignore, practise name cannot be null
//Filter by peppermint oil
if (prescription.BNFName.ToLower() != "peppermint oil")
{
return;
} //Ignore, if filtor not matched
context.EmitKeyValue(prescription.BNFName, prescription.ActualCost.ToString("0.00"));
}
}
public override void Map(string inputLine, MapperContext context)
{
var matches = commaSplit.Matches(inputLine);
//Hadoop is semi-structured, meaning that we do not need every row to match
//our expected structure. This is a simplistic check, but given a more polyglot
//data set, we could filter out unexpected rows or perform more complex filtering.
if (matches == null || matches.Count != 6)
{
//If this were a production data set, I would think about logging bad rows
//but because this is a demo, I just want to return without passing anything
//to be reduced.
return;
}
//Trim off any leading comma or surrounding quotation marks.
string key = matches[1].Value.TrimStart(',').Trim('\"');
//We don't want to return the header row.
if (key == "LCR DESC")
{
return;
}
//The Map function returns a set of key-value pairs.
//The key in this case is the specific crime, and our value
//is "1" (which we will use to get a count).
context.EmitKeyValue(key, value);
}
public override void Map(string inputLine, MapperContext context)
{
var matches = commaSplit.Matches(inputLine);
//Hadoop is semi-structured, meaning that we do not need every row to match
//our expected structure. This is a simplistic check, but given a more polyglot
//data set, we could filter out unexpected rows or perform more complex filtering.
if (matches == null || matches.Count != 6)
{
//If this were a production data set, I would think about logging bad rows
//but because this is a demo, I just want to return without passing anything
//to be reduced.
return;
}
//Trim off any leading comma or surrounding quotation marks.
string key = matches[1].Value.TrimStart(',').Trim('\"');
//We don't want to return the header row.
if (key == "LCR DESC")
{
return;
}
//The Map function returns a set of key-value pairs.
//The key in this case is the specific crime, and our value
//is "1" (which we will use to get a count).
context.EmitKeyValue(key, value);
}
public override void Map(string inputLine, MapperContext context)
{
//Step to Identify the Practice or Prescription data set
//Using the SDK, tried to use the MapperContext.InputFileName property: it is always empty
//So decided to use items count of each datasets
//Items count 8 for practice and Items count 9 for prescription
char[] delimiterChars = { ',' };
//split up the passed in line
string[] individualItems = inputLine.Trim().Split(delimiterChars);
if (individualItems.Count() == 9)
{
Prescription prescription = reader.ExtractPrescriptionsFromCsvLineFormat(inputLine);
if (String.IsNullOrWhiteSpace(prescription.PracticeId)) { return; } //Ignore, practise name cannot be null
//Filter by peppermint oil
if (prescription.BNFName.ToLower() != "peppermint oil") { return; } //Ignore, if filtor not matched
context.EmitKeyValue(prescription.BNFName, prescription.ActualCost.ToString("0.00"));
}
}
public override void Map(string inputLine, MapperContext context)
{
try
{
var parts = inputLine.Split(',');
if (parts.Length != 16)
{
return;
}
if (parts[13].Equals(""))
{
return;
}
if (parts[8].Equals(""))
{
return;
}
// avoid culture problems
string formatString = "dd/MM/yyyy HH:mm";
var start = DateTime.ParseExact(parts[4], formatString, null);
var end = DateTime.ParseExact(parts[8], formatString, null);
var key = String.Format("{0},{1}", parts[10], parts[13]);
var value = String.Format("{0},{1}", start.ToString(), end.ToString());
context.EmitKeyValue(key, value);
}
catch (Exception)
{
}
}
public override void Map(string inputLine, MapperContext context)
{
var value = int.Parse(inputLine);
var key = value % 2 == 0 ? "even" : "odd";
context.EmitKeyValue(key, value.ToString());
}
public override void Map(string inputLine, MapperContext context)
{
//interpret the incoming line as an integer value
var value = int.Parse(inputLine);
//determine whether value is even or odd
string key = value%2 == 0 ? "even" : "odd";
//output key assignment with value
context.EmitKeyValue(key, value.ToString());
}
}; //ascii 58--64 + misc.
public override void Map(string inputLine, MapperContext context)
{
foreach (string word in inputLine.Trim().Split(this._punctuationChars))
{
context.IncrementCounter("mapInputs");
context.Log(string.Format("Map:: {0},{1}", word, "1"));
context.EmitKeyValue(word, "1");
}
}
public override void Map(string inputLine, MapperContext context)
{
// The odometer is on index 2
var parts = inputLine.Split('\t');
var id = parts[0];
var kilometers = parts[2];
context.EmitKeyValue(id, kilometers);
}
public override void Map(string inputLine, MapperContext context)
{
var words = inputLine.Split(' ', '\n', '\t');
foreach (var word in words)
{
context.EmitKeyValue(word, 1.ToString());
}
}
public override void Map(string inputLine, MapperContext context)
{
// The odometer is on index 2
var parts = inputLine.Split('\t');
var id = parts[0];
var kilometers = parts[2];
context.EmitKeyValue(id, kilometers);
}
public override void Map(string inputLine, MapperContext context)
{
int inputValue = int.Parse(inputLine);
//Perform the work
double sqtr = Math.Sqrt((double)inputValue);
//write Output Data
context.EmitKeyValue(inputValue.ToString(), sqtr.ToString());
}
public override void Map(string inputLine, MapperContext context)
{
// 输入
int inputValue = int.Parse(inputLine);
// 任务
var sqrt = Math.Sqrt(inputValue);
// 写入输出
context.EmitKeyValue(inputValue.ToString(), sqrt.ToString());
}
public override void Map(string inputLine, MapperContext context)
{
int input = int.Parse(inputLine);
// Find the square root.
double root = Math.Sqrt((double)input);
// Write output.
context.EmitKeyValue(input.ToString(), root.ToString());
}
public override void Map(string inputLine, MapperContext context)
{
string[] terms = inputLine.Split('\t');
// add a sanity check in case we have a data quality issue
if (terms.Length != 6) return;
// get the country part out
string country = terms[3];
context.EmitKeyValue(country, "1");
}
public override void Map(string inputLine, MapperContext context)
{
//interpret the incoming line as an integer value
int value = int.Parse(inputLine);
//determine whether value is even or odd
string key = (value % 2 == 0) ? "even" : "odd";
//output key assignment with value
context.EmitKeyValue(key, value.ToString(CultureInfo.InvariantCulture));
}
public override void Map(string inputLine, MapperContext context)
{
string[] inputValues = inputLine.Split(',');
//Pulls all responses that link to the id of this question
if (inputValues[1].Trim() == "10001")
{
string ip = inputValues[0].Trim();
string country = IpAddressResolver.Resolve(ip);
context.EmitKeyValue(country, inputValues[2]);
}
}
public override void Map(string inputLine, MapperContext context)
{
string[] words =
inputLine.Trim().Split(new char[] { ' ', '.', '?', ',', ':', '!', '"', ')', '(', '-', '*', '$', '\'', ';', '\\', '/' },
StringSplitOptions.RemoveEmptyEntries);
for (int i = 0; i < words.Count() - 1; i++)
{
context.EmitKeyValue(words[i], words[i + 1]);
}
}
public override void Map(string inputLine, MapperContext context)
{
var dataRow = inputLine.Split('\t');
if (dataRow.Count() == 4)
{
var userId = dataRow[1];
var rating = dataRow[2];
var movieId = dataRow[3];
context.EmitKeyValue(userId, StringUtility.GetAsTabbedString(new[]{ movieId, rating}));
}
}
//Override the map method.
public override void Map(string inputLine, MapperContext context)
{
//Extract the namespace declarations in the Csharp files
var reg = new Regex(@"(using)\s[A-za-z0-9_\.]*\;");
var matches = reg.Matches(inputLine);
foreach (Match match in matches)
{
//Just emit the namespaces.
context.EmitKeyValue(match.Value, "1");
}
}
public override void Map(string inputLine, MapperContext context)
{
var dataRow = inputLine.Split('\t');
if (dataRow.Count() == 4)
{
var userId = dataRow[1];
var rating = dataRow[2];
var movieId = dataRow[3];
context.EmitKeyValue(userId, StringUtility.GetAsTabbedString(new[] { movieId, rating }));
}
}
public override void Map(string inputLine, MapperContext context)
{
string[] fields = inputLine.Split(',');
string horse = fields[0];
string jockey = fields[1];
string course = fields[2];
string stats = GetStatsForHorseJockeyCourse(
horse,
jockey,
course);
context.EmitKeyValue(horse, stats);
}
public override void Map(string inputLine, MapperContext context)
{
string[] fields = inputLine.Split(',');
string horse = fields[0];
string jockey = fields[1];
string course = fields[2];
string stats = GetStatsForHorseJockeyCourse(
horse,
jockey,
course);
context.EmitKeyValue(horse, stats);
}
public override void Map(string inputLine, MapperContext context)
{
char[] delimiterChars = { ','};
//split up the passed in line
string[] individualItems = inputLine.Trim().Split(delimiterChars);
//Step to Identify the Practice or Prescription data set
//Using the SDK, tried to use the MapperContext.InputFileName property: it is always empty
//So decided to use items count of each datasets
//Items count 8 for practice and Items count 9 for prescription
if (individualItems.Count() == 8)
{
Practices practice = practiceLinereader.ExtractPracticesFromCsvLineFormat(inputLine);
if (String.IsNullOrWhiteSpace(practice.ReferenceId)) { return; } //Ignore, practise name cannot be null
if (String.IsNullOrWhiteSpace(practice.Name)) { return; } //Ignore, practise name cannot be null
if (String.IsNullOrWhiteSpace(practice.PostCode)) { return; } //Ignore, practise name cannot be null
context.EmitKeyValue(practice.ReferenceId, Convert.ToString(practice.PostCode));
}
//Items count 9 for prescription
if (individualItems.Count() == 9)
{
Prescription prescription = prescriptionLinereader.ExtractPrescriptionsFromCsvLineFormat(inputLine);
if (String.IsNullOrWhiteSpace(prescription.PracticeId)) { return; } //Ignore, practise name cannot be null
// parctice Id with Amount
context.EmitKeyValue(prescription.PracticeId, prescription.ActualCost.ToString("0.00"));
}
}
public override void Map(string inputLine, MapperContext context)
{
//example input: Hello, Andy
if (!inputLine.StartsWith("Hello, "))
{
context.Log(string.Format("The inputLine {0} is not in the correct format", inputLine));
context.IncrementCounter("RecoverableError", "InputFormatIncorrect", 1);
return;
}
var key = inputLine.Substring(7);
if (key.EndsWith(".")) key = key.Trim('.');
context.EmitKeyValue(key, "1");//we are going to count instances, the value is irrelevant
}
public override void Map(string inputLine, MapperContext context)
{
//example input: Hello, Andy
if (!inputLine.StartsWith("Hello, "))
{
return;
}
var key = inputLine.Substring(7);
if (key.EndsWith("."))
{
key = key.Trim('.');
}
context.EmitKeyValue(key, "1");//we are going to count instances, the value is irrelevant
}
public override void Map(string inputLine, MapperContext context)
{
var PROCESSED_YEAR = 2007;
var data = ExtractValueFromLine(inputLine);
if (data.CountryName == "Country Name")
{
return;
}
if (data.YearValues.ContainsKey(PROCESSED_YEAR))
{
var trend = ComputeTrend(data.YearValues, PROCESSED_YEAR);
context.EmitKeyValue(data.IndicatorCode, data.CountryCode + '\t' + data.CountryName + '\t' + trend + '\t' + data.YearValues[PROCESSED_YEAR]);
}
}
public override void Map(string inputLine, MapperContext context)
{
string key;
// Replace '- ' with empty value, so input lines are separated only by white space
inputLine = inputLine.Replace("- ", "");
List <string> line_fields;
// Using Regex to split input lines by white space unless text enclosed with in double quotes and '[]' and store each field as list
line_fields = System.Text.RegularExpressions.Regex.Matches(inputLine, @"[\""].+?[\""]|[[].+?[]]|[^ ]+")
.Cast <System.Text.RegularExpressions.Match>()
.Select(m => m.Value)
.ToList();
context.EmitKeyValue(line_fields[3], inputLine.ToString());
}
// Gets the total number of purchases in each country across the 4 days & the % of these purchases made by new users.
// Each data row in 'clickstearm' data file is in the format...
// 'DateTime of Hit \t ProductId \t VisitorType \t Country of Request \t Referrer \t Action'
// E.g. 01/03/2013 18:51:31 159822 Regular USA Adword Purchase
public override void Map(string inputLine, MapperContext context)
{
var dataRow = inputLine.Split('\t');
if (dataRow.Count() == 6)
{
var visitorType = dataRow[2];
var country = dataRow[3];
var action = dataRow[5];
if (action == "Purchase")
{
context.IncrementCounter("HitMissProgress", "PurchaseFound", 1);
context.EmitKeyValue(country, visitorType);
}
context.IncrementCounter("HitMissProgress", "PurchaseNotFound", 1);
}
}
// Gets the total number of purchases in each country across the 4 days & the % of these purchases made by new users.
// Each data row in 'clickstearm' data file is in the format...
// 'DateTime of Hit \t ProductId \t VisitorType \t Country of Request \t Referrer \t Action'
// E.g. 01/03/2013 18:51:31 159822 Regular USA Adword Purchase
public override void Map(string inputLine, MapperContext context)
{
var dataRow = inputLine.Split('\t');
if (dataRow.Count() == 6)
{
var visitorType = dataRow[2];
var country = dataRow[3];
var action = dataRow[5];
if (action == "Purchase")
{
context.IncrementCounter("HitMissProgress", "PurchaseFound", 1);
context.EmitKeyValue(country, visitorType);
}
context.IncrementCounter("HitMissProgress", "PurchaseNotFound", 1);
}
}
public override void Map(string inputLine, MapperContext context)
{
string[] words = inputLine.Split(' ');
if (words.Count <string>() > 0)
{
//Get the datetimevalue value in the inputLine
string datetimevalue = words[3].Remove(0, 1);
//Convert the datetimevalue into into the DateTime format
string[] value = datetimevalue.Split(':');
string[] date = value[0].Split('/');
string datetime = date[2] + "-07-" + date[0] + " " + value[1] + ":" + value[2] + ":" + value[3];
DateTime dateTime = Convert.ToDateTime(datetime);
//Emit the Hour value and Ipaddress/domain values
context.EmitKeyValue(dateTime.Hour.ToString(), words[0]);
}
}
public override void Map(string inputLine, MapperContext context)
{
var matches = commaSplit.Matches(inputLine);
//Hadoop is semi-structured, meaning that we do not need every row to match
//our expected structure. This is a simplistic check, but given a more polyglot
//data set, we could filter out unexpected rows or perform more complex filtering.
if (matches == null || matches.Count != 6)
{
//If this were a production data set, I would think about logging bad rows
//but because this is a demo, I just want to return without passing anything
//to be reduced.
return;
}
//Trim off any leading comma or surrounding quotation marks.
string key = matches[5].Value.TrimStart(',').Trim('\"').Trim('(').Trim(')');
//We don't want to return the header row.
if (key == "LOCATION")
{
return;
}
//At this point, we have coordinates which look like
//35.776238687249744, -78.6246378053371
//We want to solve to 3 places after the decimal point to
//get a better idea of "neighborhood"/area-level crime.
var keyvals = key.Split(',');
if (keyvals.Length != 2)
{
return;
}
key = keyvals[0].Trim(' ').Substring(0, keyvals[0].IndexOf('.') + 4)
+ ", " + keyvals[1].Trim(' ').Substring(0, keyvals[1].IndexOf('.') + 3);
//The Map function returns a set of key-value pairs.
//The key in this case is the specific crime, and our value
//is "1" (which we will use to get a count).
context.EmitKeyValue(key, value);
}
public override void Map(string inputLine, MapperContext context)
{
//example input: Hello, Andy
if (!inputLine.StartsWith("Hello, "))
{
context.Log(string.Format("The inputLine {0} is not in the correct format", inputLine));
context.IncrementCounter("RecoverableError", "InputFormatIncorrect", 1);
return;
}
var key = inputLine.Substring(7);
if (key.EndsWith("."))
{
key = key.Trim('.');
}
context.EmitKeyValue(key, "1");//we are going to count instances, the value is irrelevant
}
public override void Map(String line, MapperContext context)
{
//context.Log(string.Format("Mapper: Input- {0}", line));
Tweet atweet = Tweet.Deserializer(line);
string polarity = SentimentAnalyser.findSentiment(atweet.Text);
int year = atweet.Time.Year;
int month = atweet.Time.Month;
string country = Country.getCountryByLongitudeLattitude(atweet.lattitude, atweet.longitude);
if (year == 2015 || year == 2014)
{
//context.IncrementCounter("HitMissProgress", "TweetOfRecentYearFound", 1);
// context.Log(string.Format("Emitting- {0} | {1}", country, polarity));
context.EmitKeyValue(country, polarity);
}
//context.IncrementCounter("HitMissProgress", "TweetOfRecentYearNOTFound", 1);
}
public override void Map(string inputLine, MapperContext context)
{
var ofertas = ServiceHelper.Deserialize<OffertResult>(inputLine);
foreach (var oferta in ofertas.offers.Where(x => x.category != null && !String.IsNullOrEmpty(x.category.value)))
{
if (oferta.province != null && !String.IsNullOrEmpty(oferta.province.value))
{
var fecha = String.Format("{0}:00:00", Convert.ToDateTime(oferta.published).Hour);
var provincia = Province.DepurarProvincia(oferta.province.value);
var linea = String.Format("{0};{1};{2}" + Environment.NewLine,
oferta.category.value,
provincia,
fecha);
context.EmitKeyValue(linea, "1");
}
}
}
public override void Map(string inputLine, MapperContext context)
{
if (inputLine.Contains(";"))
{
var array = inputLine.Split(';');
if (array.Length >= 3)
{
var provincia = Province.DepurarProvincia(array[2]);
var fecha = String.Format("{0}:00:00",
Convert.ToDateTime(array[1], new CultureInfo("es-es")).Hour);
var linea = String.Format("{0};{1};{2}" + Environment.NewLine,
array[0],
provincia,
fecha);
context.EmitKeyValue(linea, "1");
}
}
}
public override void Map(string inputLine, MapperContext context)
{
var matches = commaSplit.Matches(inputLine);
//Hadoop is semi-structured, meaning that we do not need every row to match
//our expected structure. This is a simplistic check, but given a more polyglot
//data set, we could filter out unexpected rows or perform more complex filtering.
if (matches == null || matches.Count != 6)
{
//If this were a production data set, I would think about logging bad rows
//but because this is a demo, I just want to return without passing anything
//to be reduced.
return;
}
//Trim off any leading comma or surrounding quotation marks.
string key = matches[5].Value.TrimStart(',').Trim('\"').Trim('(').Trim(')');
//We don't want to return the header row.
if (key == "LOCATION")
{
return;
}
//At this point, we have coordinates which look like
//35.776238687249744, -78.6246378053371
//We want to solve to 3 places after the decimal point to
//get a better idea of "neighborhood"/area-level crime.
var keyvals = key.Split(',');
if (keyvals.Length != 2)
{
return;
}
key = keyvals[0].Trim(' ').Substring(0, keyvals[0].IndexOf('.') + 4)
+ ", " + keyvals[1].Trim(' ').Substring(0, keyvals[1].IndexOf('.') + 3);
//The Map function returns a set of key-value pairs.
//The key in this case is the specific crime, and our value
//is "1" (which we will use to get a count).
context.EmitKeyValue(key, value);
}
public override void Map(string inputLine, MapperContext context)
{
//split line on tabs
try
{
var s = JsonConvert.DeserializeObject<Roo>(inputLine);
//get year observed
if (string.IsNullOrEmpty(s.prepTime))
{
s.prepTime = "Un";
}
//get ufo type
if (string.IsNullOrEmpty(s.name))
{
s.name = "nul";
}
context.EmitKeyValue(s.prepTime, s.name);
//send output
}
catch (InvalidCastException ex)
{
context.EmitKeyValue("error", "roor");
}
}
public override void Map(string inputLine, MapperContext context)
{
var PROCESSED_YEAR = 2007;
var data = ExtractValueFromLine(inputLine);
if (data.CountryName == "Country Name")
{
return;
}
if (data.YearValues.ContainsKey(PROCESSED_YEAR))
{
var trend = ComputeTrend(data.YearValues, PROCESSED_YEAR);
context.EmitKeyValue(data.IndicatorCode, data.CountryCode + '\t' + data.CountryName + '\t' + trend + '\t' + data.YearValues[PROCESSED_YEAR]);
}
}
public override void Map(string inputLine, MapperContext context)
{
var data = inputLine.Split('\t');
//countrycode --- name,value,originalValue
context.EmitKeyValue(data[0], data[1] + '\t' + data[2] + '\t' + data[3] + '\t' + data[4]);
}
public override void Map(string inputLine, MapperContext context)
{
var data = inputLine.Split('\t');
context.EmitKeyValue((-Double.Parse(data[1])).ToString(), inputLine);//order by value descending
}