tappyness1 commited on
Commit
d4dc4f4
β€’
1 Parent(s): eb3d6bf
Files changed (3) hide show
  1. app.py +18 -1
  2. poc.ipynb +84 -0
  3. token_secret.yaml +1 -0
app.py CHANGED
@@ -4,7 +4,7 @@ import plotly.express as px
4
  from datasets import load_dataset
5
  import os
6
 
7
- @st.cache()
8
  def bar_chart(counts_df):
9
  fig = px.bar(counts_df, x = 'car', y = 'large_vehicle')
10
 
@@ -14,6 +14,23 @@ def bar_chart(counts_df):
14
  # )
15
  return fig
16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
 
18
  def main():
19
 
 
4
  from datasets import load_dataset
5
  import os
6
 
7
+ # @st.cache()
8
  def bar_chart(counts_df):
9
  fig = px.bar(counts_df, x = 'car', y = 'large_vehicle')
10
 
 
14
  # )
15
  return fig
16
 
17
+ def daily_average(counts_df):
18
+
19
+ filtered_views_list = ['View_from_Second_Link_at_Tuas_to_sg',
20
+ 'View_from_Second_Link_at_Tuas_to_jh',
21
+ 'View_from_Tuas_Checkpoint_to_sg',
22
+ 'View_from_Tuas_Checkpoint_to_jh',
23
+ 'View_from_Woodlands_Causeway_Towards_Johor_to_sg',
24
+ 'View_from_Woodlands_Causeway_Towards_Johor_to_jh',
25
+ 'View_from_Woodlands_Checkpoint_Towards_BKE_to_sg',
26
+ 'View_from_Woodlands_Checkpoint_Towards_BKE_to_jh']
27
+
28
+ counts_df_filter_views = counts_df[counts_df['view'].isin(filtered_views_list)]
29
+ counts_df_filter_views['date'] = pd.to_datetime(counts_df_filter_views['date'])
30
+ counts_df_filter_views['day_of_week'] = counts_df_filter_views['date'].dt.day_of_week
31
+ date_view_group = counts_df_filter_views.groupby(by=['view', 'day_of_week']).mean()
32
+ date_view_group = date_view_group.reset_index()
33
+
34
 
35
  def main():
36
 
poc.ipynb ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 4,
6
+ "metadata": {},
7
+ "outputs": [
8
+ {
9
+ "name": "stderr",
10
+ "output_type": "stream",
11
+ "text": [
12
+ "Using custom data configuration tappyness1--causion-800e18f416d7678b\n",
13
+ "Found cached dataset parquet (C:/Users/neoce/.cache/huggingface/datasets/tappyness1___parquet/tappyness1--causion-800e18f416d7678b/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)\n",
14
+ "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1/1 [00:00<00:00, 937.90it/s]\n"
15
+ ]
16
+ }
17
+ ],
18
+ "source": [
19
+ "from datasets import load_dataset\n",
20
+ "import pandas as pd\n",
21
+ "import os\n",
22
+ "import yaml\n",
23
+ "\n",
24
+ "token_file = open(\"token_secret.yaml\")\n",
25
+ "token_obj = yaml.load(token_file, Loader=yaml.FullLoader)\n",
26
+ "dataset = load_dataset(\"tappyness1/causion\", use_auth_token=token_obj['TOKEN'])\n",
27
+ "counts_df = pd.DataFrame(dataset['train'])\n"
28
+ ]
29
+ },
30
+ {
31
+ "cell_type": "code",
32
+ "execution_count": 30,
33
+ "metadata": {},
34
+ "outputs": [
35
+ {
36
+ "name": "stderr",
37
+ "output_type": "stream",
38
+ "text": [
39
+ "C:\\Users\\neoce\\AppData\\Local\\Temp\\ipykernel_18912\\643665856.py:1: FutureWarning: The default value of numeric_only in DataFrameGroupBy.mean is deprecated. In a future version, numeric_only will default to False. Either specify numeric_only or select only columns which should be valid for the function.\n",
40
+ " date_view_group = counts_df_filter_views.groupby(by=['view', 'day_of_week']).mean()\n"
41
+ ]
42
+ }
43
+ ],
44
+ "source": [
45
+ "filtered_views_list = ['View_from_Second_Link_at_Tuas_to_sg',\n",
46
+ " 'View_from_Second_Link_at_Tuas_to_jh',\n",
47
+ " 'View_from_Tuas_Checkpoint_to_sg',\n",
48
+ " 'View_from_Tuas_Checkpoint_to_jh',\n",
49
+ " 'View_from_Woodlands_Causeway_Towards_Johor_to_sg',\n",
50
+ " 'View_from_Woodlands_Causeway_Towards_Johor_to_jh',\n",
51
+ " 'View_from_Woodlands_Checkpoint_Towards_BKE_to_sg',\n",
52
+ " 'View_from_Woodlands_Checkpoint_Towards_BKE_to_jh']\n",
53
+ "\n",
54
+ "counts_df_filter_views = counts_df[counts_df['view'].isin(filtered_views_list)]\n",
55
+ "counts_df_filter_views['date'] = pd.to_datetime(counts_df_filter_views['date'])\n",
56
+ "counts_df_filter_views['day_of_week'] = counts_df_filter_views['date'].dt.day_of_week\n",
57
+ "date_view_group = counts_df_filter_views.groupby(by=['view', 'day_of_week']).mean()\n",
58
+ "date_view_group = date_view_group.reset_index()"
59
+ ]
60
+ }
61
+ ],
62
+ "metadata": {
63
+ "kernelspec": {
64
+ "display_name": "6242_hw1_q1",
65
+ "language": "python",
66
+ "name": "python3"
67
+ },
68
+ "language_info": {
69
+ "codemirror_mode": {
70
+ "name": "ipython",
71
+ "version": 3
72
+ },
73
+ "file_extension": ".py",
74
+ "mimetype": "text/x-python",
75
+ "name": "python",
76
+ "nbconvert_exporter": "python",
77
+ "pygments_lexer": "ipython3",
78
+ "version": "3.8.16"
79
+ },
80
+ "orig_nbformat": 4
81
+ },
82
+ "nbformat": 4,
83
+ "nbformat_minor": 2
84
+ }
token_secret.yaml ADDED
@@ -0,0 +1 @@
 
 
1
+ TOKEN: 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