[
{
$group: {
_id: null,
totalReplies: { $sum: "$reply_count" }
}
}
]
----------------------------------------------------------------------------------
[
{
$match: {
query_id: ObjectId('67516b65b6ca73eefa8a3f35')
}
},
{
$project: {
start_date: {
$dateToString: {
format: "%Y-%m-%d %H:%M:%S",
date: {
$dateAdd: {
startDate: {
$dateAdd: {
startDate: "$start_date",
unit: "hour",
amount: 5 // Add 5 hours
}
},
unit: "minute",
amount: 30 // Add 30 minutes
}
}
}
},
end_date: {
$dateToString: {
format: "%Y-%m-%d %H:%M:%S",
date: {
$dateAdd: {
startDate: {
$dateAdd: {
startDate: "$end_date",
unit: "hour",
amount: 5 // Add 5 hours
}
},
unit: "minute",
amount: 30 // Add 30 minutes
}
}
}
},
consumer_type: 1
}
}
]
------------------------------------------------------------------
[
{
$group: {
_id: "$encapsulation_marker", // Group by the encapsulation_marker field
count: { $sum: 1 } // Count the number of documents for each encapsulation_marker
}
},
{
$project: {
// Exclude the _id field
count: 1,
}
},
{
$sort: { count: -1 } // Sort by the count in descending order
}
]
-------------------------------------------------------------------------------
[
{
$group: {
_id: "$encapsulation_marker", // Group by the encapsulation_marker field
count: { $sum: 1 } // Count the number of documents for each encapsulation_marker
}
},
{
$project: {
_id: 0, // Exclude the _id field
encapsulation_marker: "$_id", // Rename _id to encapsulation_marker
count: 1 // Include the count field
}
},
{
$sort: { encapsulation_marker: 1 } // Sort alphabetically by the encapsulation_marker field
}
]
------------------------------------------------------------------------------------------------
from pymongo import MongoClient
uri = "mongodb+srv://capabilities_dev:Uii4tTYHqf1D4pjr@capabilities-org-
dev.xz5rt.mongodb.net/"
# Establish the connection using the URI
client = MongoClient(uri)
db = client['tellagence1_66aa62ecd2fd9f2b3da2798a_org']
collections = ['olivia_rodrigo_vampire_66f6fe38804090e8f1df0a95_rac',
'api_rotation_test_6731d875048e19ca17c14035_rac',
'categorization_artist_hate_671686cbb29eb94295a3755a_rac',
'categorization_politics_vgsc_abquue_6706b6e29588a4330dc3f314_rac',
'youtube_core_shorts_h1_67058de42656dcc16fe575af_rac']
for col in collections:
collection = db[col]
cursor = collection.find({}, {"date":1})
data = pd.DataFrame(list(cursor))
data['year'] = data['date'].dt.isocalendar().year
data['month'] = data['date'].dt.month
data["year_month"] = data["year"].astype(str) + "_" + data["month"].apply(lambda x:
f"{x:02d}")
# Perform the group by operation
grouped_data = data.groupby("year_month").size()
name = "monthly" + col
pd.DataFrame(grouped_data).to_csv(f"{name}.csv")
