Spaces:
Sleeping
Sleeping
File size: 6,024 Bytes
2ac2136 b5f5199 2ac2136 fe845ab 0948ba1 fe845ab 2ac2136 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 |
import click
import pandas as pd
import graphviz
import pydot
import plotly.express as px
import matplotlib.pyplot as plt
import pycountry_convert as pc
d_tiny = pd.read_json('datasets/sample_tiny.json', lines=True)
d_small = pd.read_json('datasets/sample_small.json', lines=True)
# d_100k_lines = pd.read_json('datasets/sample_100k_lines.json', lines=True)
# d_400k_lines = pd.read_json('datasets/sample_400k_lines.json', lines=True)
def country_code_to_continent(country_code):
if country_code == "EU":
return "European Union"
elif country_code == "AP":
return "Asia/Pacific Region"
else:
try:
return pc.convert_continent_code_to_continent_name(pc.country_alpha2_to_continent_code(country_code))
except KeyError:
return "Unknown country"
def get_views_by_country(data, doc_uuid):
fig = plt.figure(figsize=(10, 6))
plt.title('Views by Country')
plt.xlabel("Countries")
plt.ylabel("No. of views")
plt.hist(data[data['subject_doc_id'] == doc_uuid]['visitor_country'])
return fig
def get_views_by_continent(data, doc_uuid):
fig = plt.figure(figsize=(10, 6))
plt.title('Views by Continent')
plt.xlabel("Continents")
plt.ylabel("No. of views")
plt.hist(data[data['subject_doc_id'] == doc_uuid]['visitor_continent'])
return fig
def get_visitor_useragents(data):
fig = plt.figure(figsize=(10, 6))
data['visitor_useragent'].value_counts().plot(kind='bar')
return fig
def get_visitor_browsers(data):
fig = plt.figure(figsize=(10, 6))
data['visitor_browser'] = data['visitor_useragent'].str.split('/').str[0]
data['visitor_browser'].value_counts().plot(kind='bar')
return fig
def get_avid_readers(data):
return data.groupby('visitor_uuid').sum(numeric_only=True)['event_readtime'].sort_values(ascending=False).head(10)
def plot_avid_readers(data):
fig = plt.figure(figsize=(11, 7))
get_avid_readers(data).sort_values(ascending=True).plot(kind='barh')
return fig
# def get_doc_visitors(doc_uuid):
# return data_tiny[data_tiny['subject_doc_id'] == doc_uuid]['visitor_uuid'].unique()
#
#
# def get_visitor_docs(visitor_uuid):
# return data_tiny[data_tiny['visitor_uuid'] == visitor_uuid]['subject_doc_id'].dropna().unique()
#
#
# def get_also_likes_doc(doc_uuid, visitor_uuid, ascending):
# visitor_uuids = get_doc_visitors(doc_uuid)
# doc_uuids = sum([list(get_visitor_docs(reader)) for reader in visitor_uuids], [])
# return pd.Series(doc_uuids).value_counts(ascending=ascending)
#
#
# def also_like(doc_uuid, visitor_uuid, ascending):
# visitor_uuids = get_doc_visitors(doc_uuid)
# y = []
# for reader in visitor_uuids:
# for doc in get_visitor_docs(reader):
# if doc != doc_uuid and doc not in get_visitor_docs(visitor_uuid).tolist():
# y.append([reader, doc])
# return pd.DataFrame(y)
# Req 5a
def get_doc_visitors(data, doc_uuid):
readers = data[data['env_type'] == "reader"]
return readers[readers['subject_doc_id'] == doc_uuid]['visitor_uuid'].unique()
# Req 5b
def get_visitor_docs(data, visitor_uuid):
readers = data[data['env_type'] == "reader"]
return readers[readers['visitor_uuid'] == visitor_uuid]['subject_doc_id'].dropna().unique()
# Req 5c, 5d
def also_like(data, doc_uuid, visitor_uuid, ascending, req_5=True):
visitor_uuids = get_doc_visitors(data, doc_uuid)
y = []
for reader in visitor_uuids:
for doc in get_visitor_docs(data, reader):
if doc != doc_uuid and doc not in get_visitor_docs(data, visitor_uuid).tolist():
y.append([reader, doc])
if not req_5:
return pd.DataFrame(y)
try:
if ascending:
print("Not Here")
return pd.DataFrame(y).groupby(1).count().nsmallest(10, [0]).reset_index().tail(-1)
else:
print("Here")
return pd.DataFrame(y).groupby(1).count().nlargest(10, [0]).reset_index().tail(-1)
except KeyError:
print("Exception thrown")
return pd.DataFrame(y)
# Req 6
def also_like_graph(data, doc_uuid, visitor_uuid, ascending):
top_docs = also_like(data, doc_uuid, visitor_uuid, ascending, req_5=False)
y = top_docs[1].value_counts()
y = pd.DataFrame(y)
# y.loc[len(y.index)] = [visitor_uuid, doc_uuid]
print(y)
dot = graphviz.Digraph()
for index, row in top_docs.iterrows():
# if(index <= 7):
# print(row[0], row[1])
dot.node(str(row[0]), str(row[0])[-4:])
dot.node(str(row[1]), str(row[1])[-4:])
dot.edge(str(row[0]), str(row[1]))
# print(dot.source)
dot.render('output.dot').replace('\\', '/')
(graph,) = pydot.graph_from_dot_file('output.dot')
graph.write_png('output.png')
return 'output.png'
# print(also_like(data_tiny, "100713205147-2ee05a98f1794324952eea5ca678c026", "b5d13a36dad1147b", False).groupby(1).count().nlargest(10, [0]))
# print(also_like("1s", "a", False).groupby(1).count())
#
@click.command()
@click.option('-u', type=str, help="user_uuid")
@click.option('-d', type=str, help="doc_uuid")
@click.option('-t', type=str, help="task_id")
@click.option('-f', type=str, help="file_name")
def run_task(u, d, t, f):
# 2a, 2b, 3a, 3b, 4, 5d, 6, 7
if t == "2a":
get_views_by_country(globals()[f"d_{f}"], d)
plt.show()
elif t == "2b":
get_views_by_continent(globals()[f"d_{f}"], d)
plt.show()
elif t == "3a":
get_visitor_useragents(globals()[f"d_{f}"])
plt.show()
elif t == "3b":
get_visitor_browsers(globals()[f"d_{f}"])
plt.show()
elif t == "4":
get_avid_readers(globals()[f"d_{f}"])
elif t == "5d":
# print(also_like('100713205147-2ee05a98f1794324952eea5ca678c026', '19c97695f06da354', False))
also_like(globals()[f"d_{f}"], d, u, False)
elif t == "6":
also_like_graph(globals()[f"d_{f}"], d, u, False)
if __name__ == '__main__':
run_task()
|