code refactoring (#2)

README.md

@@ -3,7 +3,7 @@
 
 ## one of analysis dashboard
 
-![Image](./image.png)
+![Image](./assets/image.png)
 
 ### libraries used
 - bs4

clean_stop_words.py

@@ -1,8 +1,8 @@
 import json
 
-data_file_path = 'cleared_unwanted_keys.json'  
-keys_to_remove_file_path = 'stop_words.json' 
-output_file_path = 'final_filtered_data.json' 
+data_file_path = 'outputs/cleared_unwanted_keys.json'  
+keys_to_remove_file_path = 'outputs/stop_words.json' 
+output_file_path = 'outputs/final_filtered_data.json' 
 
 with open(data_file_path, 'r', encoding='utf-8') as file:
     key_value_pairs = json.load(file) 

clear-non-alpha.py

@@ -1,10 +1,10 @@
 import json
 import re
 
-file_path = 'word_dictionary.json'
+file_path = 'outputs/word_dictionary.json'
 
-valid_keys_file = 'valid_keys.json'
-invalid_keys_file = 'invalid_keys.json'
+valid_keys_file = 'outputs/valid_keys.json'
+invalid_keys_file = 'outputs/invalid_keys.json'
 
 with open(file_path, 'r', encoding='utf-8') as file:
     data = json.load(file)

process.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+if [ "$#" -ne 1 ]; then
+    echo "Usage: $0 <top_n>"
+    exit 1
+fi
+
+top_n="$1"
+
+python_files=(
+    # "words-extractor.py"
+    # "clear-non-alpha.py"
+    # "separate.py"
+    # "remove_unwanted_chars_from_keys.py"
+    "clean_stop_words.py"
+)
+
+for file in "${python_files[@]}"
+do
+    echo "Running $file..."
+    python "$file"
+    if [ $? -ne 0 ]; then
+        echo "Error: $file failed to run."
+        exit 1
+    fi
+    echo "$file completed successfully."
+done
+
+echo "Running TOP  $top_n..."
+python "top-words.py" $top_n
+if [ $? -ne 0 ]; then
+    echo "Error: $last_file failed to run."
+    exit 1
+fi
+
+echo "All Processing is done executed."

remove-duplicates.py

@@ -1,10 +1,10 @@
 import json
 
 # Path to the input JSON file containing an array of words
-input_file_path = 'stop_words.json'
+input_file_path = 'outputs/stop_words.json'
 
 # Path to the output JSON file where unique words will be saved
-output_file_path = 'unique_words.json'
+output_file_path = 'outputs/unique_words.json'
 
 # Open and load the JSON file
 with open(input_file_path, 'r', encoding='utf-8') as file:

remove_unwanted_chars_from_keys.py

@@ -2,10 +2,10 @@
 import re
 
 # Path to the input JSON file with key-value pairs
-input_file_path = 'non_english_keys.json'
+input_file_path = 'outputs/non_english_keys.json'
 
 # Path to the output JSON file where filtered key-value pairs will be saved
-output_file_path = 'cleared_unwanted_keys.json'
+output_file_path = 'outputs/cleared_unwanted_keys.json'
 
 # Regular expressions for identifying unwanted characters in keys
 symbols_pattern = re.compile(r'[^\w\s]', re.UNICODE)  # Matches any symbols (excluding alphanumeric and whitespace)

separate.py

@@ -1,11 +1,11 @@
 import json
 import re
 
-file_path = 'valid_keys.json'
+file_path = 'outputs/valid_keys.json'
 
 # Output file paths
-english_keys_file = 'english_keys.json'
-non_english_keys_file = 'non_english_keys.json'
+english_keys_file = 'outputs/english_keys.json'
+non_english_keys_file = 'outputs/non_english_keys.json'
 
 # Open and load the JSON file
 with open(file_path, 'r', encoding='utf-8') as file: