編集履歴

質問編集履歴

もう一度考えます。

2019/08/15 06:23

投稿

jyon

スコア13

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -1,36 +1,8 @@
-```python
+#!/usr/bin/env python3
-import text
+# -*- coding: utf-8 -*-
-stopwords =["そう",","/"]
-kw_volume=[]
-mid=[]
-for i in range(len(test1)):
-    mid=text.count_csv_noun(sentences[i])
-    result=[]
-    for x in mid:
-        if not x[0] in stopwords:
-            x[1]=int(x[1])
-            x = tuple(x)
-            result.append(x)
-    kw_volume.append(result)
-```
-```python(test)
 import MeCab as mc
@@ -65,271 +37,3 @@
     if args.word_count:
         return '{}'.format(word_line(args.word_count))
-#文字数カウントの関数の追加
-def word_line(input_text):
-    with open(input_text) as f:
-        lines = f.readlines()
-    return len(lines)
-#allバージョン
-def mecab_analysis_all(text):
-    t = mc.Tagger("-Ochasen")
-    t.parse('')
-    node = t.parseToNode(text)
-    output = []
-    while node:
-        if node.surface != "":  # ヘッダとフッタを除外
-            word_type = node.feature.split(",")[0]
-            if word_type in [ "動詞","名詞","形容詞"]:
-                output.append(node.surface)
-        node = node.next
-        if node is None:
-            break
-    return output
-#名詞バージョン
-def mecab_analysis_noun(text):
-    t = mc.Tagger("-Ochasen")
-    t.parse('')
-    node = t.parseToNode(text)
-    output = []
-    while node:
-        if node.surface != "":  # ヘッダとフッタを除外
-            word_type = node.feature.split(",")[0]
-            if word_type in [ "名詞"]:
-                output.append(node.surface)
-        node = node.next
-        if node is None:
-            break
-    return output
-#動詞バージョン
-def mecab_analysis_verb(text):
-    t = mc.Tagger("-Ochasen")
-    t.parse('')
-    node = t.parseToNode(text)
-    output = []
-    while node:
-        if node.surface != "":  # ヘッダとフッタを除外
-            word_type = node.feature.split(",")[0]
-            if word_type in [ "動詞"]:
-                output.append(node.surface)
-        node = node.next
-        if node is None:
-            break
-    return output
-#形容詞バージョン
-def mecab_analysis_adjective(text):
-    t = mc.Tagger("-Ochasen")
-    t.parse('')
-    node = t.parseToNode(text)
-    output = []
-    while node:
-        if node.surface != "":  # ヘッダとフッタを除外
-            word_type = node.feature.split(",")[0]
-            if word_type in [ "形容詞"]:
-                output.append(node.surface)
-        node = node.next
-        if node is None:
-            break
-    return output
-#inputはテキスト
-#all
-def count_csv_all(text_input):
-    text= str(text_input)
-    words = mecab_analysis_all(text)
-    counter = Counter(words)
-    output = []
-    for word, count in counter.most_common():
-        if len(word) > 0:
-            middle = [word,count]
-            output.append(middle)
-    return output
-#noun
-def count_csv_noun(text_input):
-    text= str(text_input)
-    words = mecab_analysis_noun(text)
-    counter = Counter(words)
-    output = []
-    for word, count in counter.most_common():
-        if len(word) > 0:
-            middle = [word,count]
-            output.append(middle)
-    return output
-#verb
-def count_csv_verb(text_input):
-    text= str(text_input)
-    words = mecab_analysis_verb(text)
-    counter = Counter(words)
-    output = []
-    for word, count in counter.most_common():
-        if len(word) > 0:
-            middle = [word,count]
-            output.append(middle)
-    return output
-#adjective
-def count_csv_adjective(text_input):
-    text= str(text_input)
-    words = mecab_analysis_verb(text)
-    counter = Counter(words)
-    output = []
-    for word, count in counter.most_common():
-        if len(word) > 0:
-            middle = [word,count]
-            output.append(middle)
-    return output
-def banner():
- print("単語,出現回数")
-if __name__ == '__main__':
-    #banner()
-    result = parser()
-    print(result)
-```
-kw_volumeとmidをprintで出力すると、何もデータが入ってないんですが、それはなぜでしょうか。

書式の変更

2019/08/15 06:23

投稿

jyon

スコア13

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -1,3 +1,5 @@
+```python
 import text
 stopwords =["そう",","/"]
@@ -26,6 +28,308 @@
     kw_volume.append(result)
+```
+```python(test)
+import MeCab as mc
+from collections import Counter
+from argparse import ArgumentParser
+def parser():
+    usage = 'Usage:python3 count_word.py [-t <FILE.txt>] [--help]'\
+            .format(__file__)
+    parser = ArgumentParser(usage=usage)
+    parser.add_argument('-l','--word_count_line',dest='word_count',help='行数' )
+    parser.add_argument('-w','--number_of_words',dest='number_of_words',help='単語数' )
+    args = parser.parse_args()
+    if args.number_of_words:
+        return '{}'.format(count_csv(args.number_of_words))
+    if args.word_count:
+        return '{}'.format(word_line(args.word_count))
+#文字数カウントの関数の追加
+def word_line(input_text):
+    with open(input_text) as f:
+        lines = f.readlines()
+    return len(lines)
+#allバージョン
+def mecab_analysis_all(text):
+    t = mc.Tagger("-Ochasen")
+    t.parse('')
+    node = t.parseToNode(text)
+    output = []
+    while node:
+        if node.surface != "":  # ヘッダとフッタを除外
+            word_type = node.feature.split(",")[0]
+            if word_type in [ "動詞","名詞","形容詞"]:
+                output.append(node.surface)
+        node = node.next
+        if node is None:
+            break
+    return output
+#名詞バージョン
+def mecab_analysis_noun(text):
+    t = mc.Tagger("-Ochasen")
+    t.parse('')
+    node = t.parseToNode(text)
+    output = []
+    while node:
+        if node.surface != "":  # ヘッダとフッタを除外
+            word_type = node.feature.split(",")[0]
+            if word_type in [ "名詞"]:
+                output.append(node.surface)
+        node = node.next
+        if node is None:
+            break
+    return output
+#動詞バージョン
+def mecab_analysis_verb(text):
+    t = mc.Tagger("-Ochasen")
+    t.parse('')
+    node = t.parseToNode(text)
+    output = []
+    while node:
+        if node.surface != "":  # ヘッダとフッタを除外
+            word_type = node.feature.split(",")[0]
+            if word_type in [ "動詞"]:
+                output.append(node.surface)
+        node = node.next
+        if node is None:
+            break
+    return output
+#形容詞バージョン
+def mecab_analysis_adjective(text):
+    t = mc.Tagger("-Ochasen")
+    t.parse('')
+    node = t.parseToNode(text)
+    output = []
+    while node:
+        if node.surface != "":  # ヘッダとフッタを除外
+            word_type = node.feature.split(",")[0]
+            if word_type in [ "形容詞"]:
+                output.append(node.surface)
+        node = node.next
+        if node is None:
+            break
+    return output
+#inputはテキスト
+#all
+def count_csv_all(text_input):
+    text= str(text_input)
+    words = mecab_analysis_all(text)
+    counter = Counter(words)
+    output = []
+    for word, count in counter.most_common():
+        if len(word) > 0:
+            middle = [word,count]
+            output.append(middle)
+    return output
+#noun
+def count_csv_noun(text_input):
+    text= str(text_input)
+    words = mecab_analysis_noun(text)
+    counter = Counter(words)
+    output = []
+    for word, count in counter.most_common():
+        if len(word) > 0:
+            middle = [word,count]
+            output.append(middle)
+    return output
+#verb
+def count_csv_verb(text_input):
+    text= str(text_input)
+    words = mecab_analysis_verb(text)
+    counter = Counter(words)
+    output = []
+    for word, count in counter.most_common():
+        if len(word) > 0:
+            middle = [word,count]
+            output.append(middle)
+    return output
+#adjective
+def count_csv_adjective(text_input):
+    text= str(text_input)
+    words = mecab_analysis_verb(text)
+    counter = Counter(words)
+    output = []
+    for word, count in counter.most_common():
+        if len(word) > 0:
+            middle = [word,count]
+            output.append(middle)
+    return output
+def banner():
+ print("単語,出現回数")
+if __name__ == '__main__':
+    #banner()
+    result = parser()
+    print(result)
+```
 kw_volumeとmidをprintで出力すると、何もデータが入ってないんですが、それはなぜでしょうか。