Update app.py

app.py

@@ -7,7 +7,7 @@ from tqdm import tqdm
 
 import altair as alt
 import matplotlib.pyplot as plt
-import datetime
+from datetime import date, timedelta
 
 from transformers import AutoTokenizer, AutoConfig, AutoModel, AutoModelForSequenceClassification
 
@@ -177,10 +177,44 @@ def freq(output_file, input_checks):
 
 
 def dist(output_file, input_checks):
+    #data = pd.DataFrame({
+    #'Date': ['1/1', '1/1', '1/1', '1/1', '1/1', '1/1', '2/1', '2/1', '2/1', '2/1', '2/1', '2/1', '3/1', '3/1', '3/1', '3/1', '3/1', '3/1'],
+    #'Frequency': [3, 5, 1, 8, 2, 3, 4, 7, 1, 12, 4, 2, 3, 6, 3, 10, 3, 4],
+    #'Emotion category': ['neutral', 'anger', 'fear', 'joy', 'love', 'sadness', 'neutral', 'anger', 'fear', 'joy', 'love', 'sadness', 'neutral', 'anger', 'fear', 'joy', 'love', 'sadness']})
+
+    f = open("showcase/data.txt", 'r')
+    data = f.read().split("\n")
+    f.close()
+    data = [line.split("\t") for line in data[1:-1]]
+    
+    freq_dict = {}
+    for line in data:
+    	dat = str(date(2000+int(line[0].split("/")[2]), int(line[0].split("/")[1]), int(line[0].split("/")[0])))
+    	if dat not in freq_dict.keys():
+    		freq_dict[dat] = {}
+    		if line[1] not in freq_dict[dat].keys():
+    			freq_dict[dat][line[1]] = 1
+    		else:
+    			freq_dict[dat][line[1]] += 1
+    	else:
+    		if line[1] not in freq_dict[dat].keys():
+    			freq_dict[dat][line[1]] = 1
+    		else:
+    			freq_dict[dat][line[1]] += 1
+    
+    start_date = date(2000+int(data[0][0].split("/")[2]), int(data[0][0].split("/")[1]), int(data[0][0].split("/")[0]))
+    end_date = date(2000+int(data[-1][0].split("/")[2]), int(data[-1][0].split("/")[1]), int(data[-1][0].split("/")[0]))
+    delta = end_date - start_date   # returns timedelta
+    date_range = [str(start_date + timedelta(days=i)) for i in range(delta.days + 1)]
+    
+    dates = [dat for dat in date_range for i in range(6)]
+    frequency = [freq_dict[dat][emotion] if (dat in freq_dict.keys() and emotion in freq_dict[dat].keys()) else 0 for dat in date_range for emotion in ['neutral', 'anger', 'fear', 'joy', 'love', 'sadness']]
+    categories = [emotion for dat in date_range for emotion in ['neutral', 'anger', 'fear', 'joy', 'love', 'sadness']]
+    
     data = pd.DataFrame({
-    'Date': ['1/1', '1/1', '1/1', '1/1', '1/1', '1/1', '2/1', '2/1', '2/1', '2/1', '2/1', '2/1', '3/1', '3/1', '3/1', '3/1', '3/1', '3/1'],
-    'Frequency': [3, 5, 1, 8, 2, 3, 4, 7, 1, 12, 4, 2, 3, 6, 3, 10, 3, 4],
-    'Emotion category': ['neutral', 'anger', 'fear', 'joy', 'love', 'sadness', 'neutral', 'anger', 'fear', 'joy', 'love', 'sadness', 'neutral', 'anger', 'fear', 'joy', 'love', 'sadness']})
+    	'Date': dates,
+    	'Frequency': frequency,
+    	'Emotion category': categories})
 
     domain = ['neutral', 'anger', 'fear', 'joy', 'love', 'sadness']
     range_ = ['#999999', '#b22222', '#663399', '#ffcc00', '#db7093', '#6495ed']