Python SDK Examples
This guide demonstrates comprehensive examples of using the Sentor Python SDK.
Installation
pip install sentor-python-sdkBasic Usage
from sentor import SentorClient
# Initialize the client
client = SentorClient('your-api-key')
# Analyze sentiment
input_data = [
{
"doc": "In the competitive landscape of consumer electronics, Apple and Samsung continue to lead the market with innovative products and strong brand loyalty. While Apple focuses on a tightly integrated ecosystem with devices like the iPhone, iPad, and Mac, Samsung excels in offering a wide range of options across various price points, especially in its Galaxy smartphone lineup. Both companies push the boundaries of technology, from cutting-edge chipsets to advanced camera systems, often setting industry trends that others follow.",
"doc_id": "0",
"entities": [
"Apple",
"Samsung",
"camera"
]
},
{
"doc": "Apple's new iPhone is amazing!",
"doc_id": "1",
"entities": [
"Apple",
"iPhone"
]
},
{
"doc": "Samsung's new phone is amazing!",
"doc_id": "2",
"entities": [
"Samsung",
"phone"
]
}
]
result = client.predict(input_data)
print(result)Sample Output
{
"results": [
{
"doc_id": "0",
"predicted_class": 2,
"predicted_label": "positive",
"probabilities": {
"negative": 0.00007679959526285529,
"neutral": 0.0002924697764683515,
"positive": 0.9996306896209717
},
"details": [
{
"sentence_index": 0,
"sentence_text": "In the competitive landscape of consumer electronics, Apple and Samsung continue to lead the market with innovative products and strong brand loyalty.",
"predicted_class": 2,
"predicted_label": "positive",
"probabilities": {
"negative": 0.00009389198385179043,
"neutral": 0.00032428017584607005,
"positive": 0.9995818734169006
}
},
{
"sentence_index": 1,
"sentence_text": "While Apple focuses on a tightly integrated ecosystem with devices like the iPhone, iPad, and Mac, Samsung excels in offering a wide range of options across various price points, especially in its Galaxy smartphone lineup.",
"predicted_class": 2,
"predicted_label": "positive",
"probabilities": {
"negative": 0.00005746580063714646,
"neutral": 0.00012963586777914315,
"positive": 0.99981290102005
}
},
{
"sentence_index": 2,
"sentence_text": "Both companies push the boundaries of technology, from cutting-edge chipsets to advanced camera systems, often setting industry trends that others follow.",
"predicted_class": 2,
"predicted_label": "positive",
"probabilities": {
"negative": 0.00006366783054545522,
"neutral": 0.00044553453335538507,
"positive": 0.9994907379150391
}
}
]
},
{
"doc_id": "1",
"predicted_class": 2,
"predicted_label": "positive",
"probabilities": {
"negative": 0.00010637375817168504,
"neutral": 0.0002509312762413174,
"positive": 0.9996427297592163
},
"details": [
{
"sentence_index": 0,
"sentence_text": "Apple's new iPhone is amazing!",
"predicted_class": 2,
"predicted_label": "positive",
"probabilities": {
"negative": 0.00010637375817168504,
"neutral": 0.0002509312762413174,
"positive": 0.9996427297592163
}
}
]
},
{
"doc_id": "2",
"predicted_class": 2,
"predicted_label": "positive",
"probabilities": {
"negative": 0.00010637375817168504,
"neutral": 0.0002509312762413174,
"positive": 0.9996427297592163
},
"details": [
{
"sentence_index": 0,
"sentence_text": "Samsung's new phone is amazing!",
"predicted_class": 2,
"predicted_label": "positive",
"probabilities": {
"negative": 0.00010637375817168504,
"neutral": 0.0002509312762413174,
"positive": 0.9996427297592163
}
}
]
}
]
}Clustering Documents
from sentor import SentorClient
client = SentorClient('your-api-key')
# Prepare documents for clustering (minimum 5 required)
documents = [
{
"doc_id": "doc1",
"text": "Apple announced new iPhone features with improved camera.",
"entities": ["Apple", "iPhone", "camera"]
},
{
"doc_id": "doc2",
"text": "Samsung launched Galaxy with advanced AI capabilities.",
"entities": ["Samsung", "Galaxy", "AI"]
},
{
"doc_id": "doc3",
"text": "Apple plans to integrate AI into iOS ecosystem.",
"entities": ["Apple", "AI", "iOS"]
},
{
"doc_id": "doc4",
"text": "SpaceX successfully launched Starlink satellites.",
"entities": ["SpaceX", "Starlink", "satellites"]
},
{
"doc_id": "doc5",
"text": "Bitcoin price surged after ETF approval.",
"entities": ["Bitcoin", "ETF"]
}
]
# Cluster documents
clustering_result = client.cluster(documents, language='en')
print(f"Total clusters: {clustering_result['total_clusters']}")
print(f"Outliers: {clustering_result['outliers']}")
for cluster in clustering_result['clusters']:
print(f"\nCluster {cluster['cluster_id']}:")
print(f" Documents: {len(cluster['documents'])}")
print(f" Top words: {', '.join(cluster['top_words'][:5])}")
print(f" Entities: {', '.join(cluster['entities'][:5])}")Generating Topic Names
from sentor import SentorClient
client = SentorClient('your-api-key')
# After clustering, generate topic names for each cluster
clustering_result = client.cluster(documents, language='en')
for cluster in clustering_result['clusters']:
topic_result = client.generate_topic_name(
cluster_id=cluster['cluster_id'],
documents=cluster['documents'],
entities=cluster['entities'],
top_words=cluster['top_words'],
language='en'
)
print(f"Cluster {cluster['cluster_id']}: {topic_result['topic_name']}")Complete Workflow Example
from sentor import SentorClient
import time
client = SentorClient('your-api-key')
# Step 1: Analyze sentiment
input_data = [
{
"doc": "Apple's new iPhone camera is incredible, but battery life is disappointing.",
"doc_id": "review1",
"entities": ["Apple", "iPhone", "camera", "battery life"]
},
{
"doc": "Samsung Galaxy has amazing features and great performance.",
"doc_id": "review2",
"entities": ["Samsung", "Galaxy", "features", "performance"]
},
# ... more reviews (need at least 5 for clustering)
]
sentiment_results = client.predict(input_data)
# Step 2: Extract documents for clustering
cluster_documents = []
for result in sentiment_results['results']:
original_doc = next(d for d in input_data if d['doc_id'] == result['doc_id'])
cluster_documents.append({
"doc_id": result['doc_id'],
"text": original_doc['doc'],
"entities": original_doc['entities']
})
# Step 3: Cluster documents (if enough documents)
if len(cluster_documents) >= 5:
clustering_result = client.cluster(cluster_documents)
# Step 4: Generate topic names for each cluster
for cluster in clustering_result['clusters']:
topic_result = client.generate_topic_name(
cluster_id=cluster['cluster_id'],
documents=cluster['documents'],
entities=cluster['entities'],
top_words=cluster['top_words']
)
print(f"\n=== {topic_result['topic_name']} ===")
print(f"Documents in cluster: {len(cluster['documents'])}")
# Calculate sentiment distribution
sentiments = {"positive": 0, "neutral": 0, "negative": 0}
for doc in cluster['documents']:
sentiment_data = next(
r for r in sentiment_results['results']
if r['doc_id'] == doc['doc_id']
)
sentiments[sentiment_data['predicted_label']] += 1
print(f"Sentiment distribution: {sentiments}")Error Handling
from sentor.exceptions import (
SentorAPIError,
RateLimitError,
AuthenticationError
)
def handle_prediction(documents: list):
try:
result = client.predict(documents)
return result
except RateLimitError as e:
print(f"Rate limit exceeded. Retry after {e.retry_after} seconds")
time.sleep(e.retry_after)
return client.predict(documents)
except AuthenticationError:
print("Invalid API key or authentication failed")
raise
except SentorAPIError as e:
print(f"API Error: {e.message} (Code: {e.code})")
raiseFor more examples and detailed documentation, please refer to: