feat: BDA2

1 files changed, 38 insertions, 0 deletions

diff --git a/BDA/tp2.py b/BDA/tp2.py
new file mode 100644
index 0000000..6b5b00e
--- /dev/null
+++ b/BDA/tp2.py
@@ -0,0 +1,38 @@
+from mrjob.job import MRJob
+from mrjob.step import MRStep
+import re
+
+WORD_RE = re.compile(r"[\w']+")
+
+class MRWordFrequencyCount(MRJob):
+
+    def mapper(self, _, line):
+        for word in WORD_RE.findall(line):
+            yield word, 1
+    def steps(self):
+        return [
+            MRStep(mapper=self.mapper,
+                   reducer=self.reducer_count_words),
+            MRStep(reducer=self.reducer_find_max_word)
+        ]
+
+    def reducer_count_words(self, key, values):
+        yield None, (sum(values), key)
+    def reducer_find_max_word(self, _, kvp):
+        yield max(kvp)
+
+class MRLongestWord(MRJob):
+
+    def mapper(self, _, line):
+        for word in WORD_RE.findall(line):
+            yield word, len(word)
+
+    def combiner(self, word, len_word):
+        yield None, (len_word[0], word)
+
+    def reducer(self, _, len_word):
+        yield max(len_word)
+
+if __name__ == '__main__':
+#MRWordFrequencyCount.run()
+    MRLongestWord.run()