将 JSON 数据转换为 Pandas DataFrame [关闭]

Question

"{\".travis.yml\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"fleetspeak/client-mac/com.google.code.fleetspeak.plist\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"mol123\"]}, \"count\": 1}, \"fleetspeak/src/client/client/client.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"mol123\"]}, \"count\": 1}, \"fleetspeak/src/client/client_test.go\": {\"auth_count\": 2, \"authors\": {\"py/set\": [\"Ben Galehouse\", \"mol123\"]}, \"count\": 2}, \"fleetspeak/src/client/entry/entry_unix.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"mol123\"]}, \"count\": 1}, \"fleetspeak/src/client/entry/entry_windows.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"mol123\"]}, \"count\": 1}, \"fleetspeak/src/client/entry/wait_unix.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"mol123\"]}, \"count\": 1}, \"fleetspeak/src/client/entry/wait_windows.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"mol123\"]}, \"count\": 1}, \"fleetspeak/src/client/services.go\": {\"auth_count\": 2, \"authors\": {\"py/set\": [\"Ben Galehouse\", \"mol123\"]}, \"count\": 2}, \"fleetspeak/src/client/socketservice/checks/sock_checks_windows.go\": {\"auth_count\": 2, \"authors\": {\"py/set\": [\"Ben Galehouse\", \"Brendan Jackman\"]}, \"count\": 5}, \"fleetspeak/src/e2etesting/README.md\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"fleetspeak/src/e2etesting/balancer/balancer.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 2}, \"fleetspeak/src/e2etesting/e2etest.sh\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 2}, \"fleetspeak/src/e2etesting/localtesting/end_to_end_test.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"fleetspeak/src/e2etesting/run_end_to_end_tests.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 5}, \"fleetspeak/src/e2etesting/setup/setup_components.go\": {\"auth_count\": 2, \"authors\": {\"py/set\": [\"mol123\", \"Alexandr Tsaplin\"]}, \"count\": 7}, \"fleetspeak/src/e2etesting/tests/end_to_end_tests.go\": {\"auth_count\": 2, \"authors\": {\"py/set\": [\"mol123\", \"Alexandr Tsaplin\"]}, \"count\": 5}, \"fleetspeak/src/inttesting/frr/frr.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"fleetspeak/src/inttesting/frr/proto/fleetspeak_frr/frr.pb.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"fleetspeak/src/inttesting/frr/proto/fleetspeak_frr/frr.proto\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"fleetspeak/src/inttesting/integrationtest/frr.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"tsehori\"]}, \"count\": 1}, \"fleetspeak/src/server/comms.go\": {\"auth_count\": 2, \"authors\": {\"py/set\": [\"Ben Galehouse\", \"mol123\"]}, \"count\": 4}, \"fleetspeak/src/server/components/components.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"fleetspeak/src/server/components/prometheus/prometheus.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"tsehori\"]}, \"count\": 1}, \"fleetspeak/src/server/components/proto/fleetspeak_components/config.pb.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"fleetspeak/src/server/components/proto/fleetspeak_components/config.proto\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"fleetspeak/src/server/internal/services/manager.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"tsehori\"]}, \"count\": 1}, \"fleetspeak/src/server/server.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"fleetspeak/src/server/servertests/comms_test.go\": {\"auth_count\": 2, \"authors\": {\"py/set\": [\"Ben Galehouse\", \"mol123\"]}, \"count\": 4}, \"fleetspeak/src/server/stats.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"tsehori\"]}, \"count\": 1}, \"fleetspeak/src/server/stats/collector.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"tsehori\"]}, \"count\": 1}, \"fleetspeak/test.sh\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"frr_python/frr_server.py\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"frr_python/setup.py\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"go.mod\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"mol123\"]}, \"count\": 1}, \"go.sum\": {\"auth_count\": 2, \"authors\": {\"py/set\": [\"Ben Galehouse\", \"mol123\"]}, \"count\": 3}, \"terraform/README.md\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 2}, \"terraform/cloudtesting/end_to_end_test.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"terraform/fleetspeak_configurator/build_configs.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 3}, \"terraform/fs_client_start.sh\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 2}, \"terraform/fs_server_start.sh\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"terraform/main.tf\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 3}, \"terraform/main_vm_start.sh\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 4}, \"terraform/master_server_start.sh\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 1}, \"terraform/test_runner/run_tests.go\": {\"auth_count\": 1, \"authors\": {\"py/set\": [\"Alexandr Tsaplin\"]}, \"count\": 3}}"

大家好，

我想将 JSON 数据（存储在 result.json 文件中）转换为数据帧。

我希望我的数据框看起来像所附图片中的那样。

谢谢大家:)

Answer 1

您可以将 JSON 读入数据框，然后将作者从列表转换为字符串：

# read json from string `s` to a dataframe
df = (pd.read_json(s).T
    .reset_index()
    .rename(columns={'index': 'Filename', 'auth_count': 'authors_count'}))

# convert lists of authors to comma-separated strings
df['authors'] = df['authors'].apply(lambda x: ', '.join(x['py/set']))

df

输出：

               Filename authors_count              authors count
0           .travis.yml             1     Alexandr Tsaplin     1
1   fleetspeak/clien...             1               mol123     1
2   fleetspeak/src/c...             1               mol123     1
3   fleetspeak/src/c...             2  Ben Galehouse, m...     2
4   fleetspeak/src/c...             1               mol123     1
5   fleetspeak/src/c...             1               mol123     1
6   fleetspeak/src/c...             1               mol123     1