Flussi ta' Ħidma tad-Data bl-Interpretu tal-Kodiċi
F'din il-paġna
Lezzjoni aġġornata fit-2 ta’ Novembru 2026 abbażi tad-dokumentazzjoni ta’ OpenAI: l-għodda Code Interpreter teħtieġ parametru
container(miżjud mal-eżempji kollha), il-partijiet tat-test tal-input huma tat-tipinput_text, u t-tiftix fuq il-web juża l-għoddaweb_search(web_search_previewissa hija għodda antika mingħajr filtri tad-dominju). Il-fajls iġġenerati jiġu rkuprati bl-użu tal-funzjonijietfichiers_generesutelechargermil-Lezzjoni 10. Il-fajls mehmuża mal-messaġġ jittellgħaw bl-iskopuser_data, li OpenAI tirrakkomanda għall-inputs tal-mudell (File inputs). Sorsi: Code Interpreter · Web search.
Flussi ta’ Ħidma tad-Data bl-Interpretu tal-Kodiċi
Il-lezzjonijiet preċedenti koprew kompiti individwali wieħed wara l-ieħor. L-analiżi reali tgħaqqadhom flimkien: timporta, tnaddaf, tikkalkula, tivviżwalizza u tesporta. Hija l-katina—mhux kull pass iżolat—li tieħu l-ħin meta ssir manwalment.
L-erba’ flussi ta’ ħidma hawn taħt huma każijiet reali, deliberatament varjati: rappurtar perjodiku, analiżi tal-imġiba matul iż-żmien, segmentazzjoni u tbassir. Aqrahom inqas għall-kodiċi u aktar għall-istruttura tal-prompt—numerata, espliċita dwar ir-riżultati mistennija, u preċiża dwar il-format. Din l-istruttura tbiddel talba vaga f’rapportazzjoni operattiva, u tista’ tapplikaha direttament għad-data tiegħek stess.
Fluss ta’ Ħidma 1: Rapport Finanzjarju Awtomatizzat
Ir-rappurtar perjodiku huwa l-aħjar kandidat għall-awtomazzjoni għal raġuni sempliċi: il-fajls jinbidlu, iżda l-istruttura tar-rapport le. Ladarba tikteb u tivvalida l-prompt għal xahar, jaħdem għall-ħdax-il xahar li jmiss. Innota l-istruzzjoni finali, li titlob esportazzjoni Excel għal kull taqsima. Dan jagħmel ir-riżultat direttament kondiviżibbli, minflok ma jħallik b’test li jeħtieġ riformattar.
from openai import OpenAI
client = OpenAI()
# Upload source files
files = {}
for name in ["revenus_2025.xlsx", "depenses_2025.xlsx", "budget_previsionnel.xlsx"]:
with open(name, "rb") as f:
file_obj = client.files.create(file=f, purpose="user_data")
files[name] = file_obj.id
content = [
{"type": "input_text", "text": (
"Generate a complete financial report from these 3 files: "
"1. SUMMARY: Total revenue, gross margin, net income "
"2. MONTHLY ANALYSIS: Month-over-month evolution with variations "
"3. BUDGET VARIANCES: Actual vs. forecast comparison, significant variances "
"4. CHARTS: "
" - Revenue and expenses evolution (dual axis) "
" - Budget variance waterfall "
" - Expense breakdown by category "
"5. EXPORT: Excel file with one tab per section"
)}
]
for fid in files.values():
content.append({"type": "input_file", "file_id": fid})
response = client.responses.create(
model="gpt-5.6-terra",
input=[{"role": "user", "content": content}],
tools=[{"type": "code_interpreter", "container": {"type": "auto"}}],
instructions=(
"Produce a professional report. "
"Display figures with thousands separators. "
"Use European format (decimal comma). "
"Comment on each significant variance (> 5%)."
)
)
# Retrieve all generated files
for ann in fichiers_generes(response):
telecharger(client, ann, f"sortie_{ann.filename}")
print(f"Generated: {ann.filename}")
Fluss ta’ Ħidma 2: Analiżi tal-Kohort
L-analiżi tal-kohort issegwi gruppi ffurmati fl-istess data tad-dħul matul iż-żmien. Ftit timijiet iwettqu dan il-kalkolu regolarment għax it-twaqqif tiegħu huwa tedjanti. Eżattament għalhekk iħallas li tiddelegah: il-loġika hija standard; tibdel biss id-data.
with open("utilisateurs.csv", "rb") as f:
file_obj = client.files.create(file=f, purpose="user_data")
response = client.responses.create(
model="gpt-5.6-terra",
input=[{
"role": "user",
"content": [
{"type": "input_text", "text": (
"Perform a cohort analysis on this user data: "
"1. Define cohorts by signup month "
"2. Calculate retention rate per cohort (month 1, 2, ..., 12) "
"3. Create a retention heatmap "
"4. Identify the cohort with the best retention "
"5. Estimate LTV per cohort "
"6. Export the retention table as CSV"
)},
{"type": "input_file", "file_id": file_obj.id}
]
}],
tools=[{"type": "code_interpreter", "container": {"type": "auto"}}],
instructions=(
"Show the code step by step. "
"Display intermediate results. "
"For the heatmap, use a green palette (dark = good, light = low). "
"Annotate each cell with the percentage."
)
)
Fluss ta’ Ħidma 3: Punteġġ u Segmentazzjoni
Hawnhekk, il-mudell mhux biss jiddeskrivi d-data; jibni punteġġ u jifforma gruppi. Dan jeħtieġ prekawzjoni: dejjem itlob il-metodu flimkien mar-riżultat. Segment bħal “klijenti f’riskju” mingħajr il-kriterji li pproduċewh ma jintużax: ħadd ma jista’ jikkontestah, jirriproduċih jew jikkoreġih.
def segmenter_clients(file_path: str) -> dict:
"""Segments customers using RFM and clustering."""
with open(file_path, "rb") as f:
file_obj = client.files.create(file=f, purpose="user_data")
response = client.responses.create(
model="gpt-5.6-terra",
input=[{
"role": "user",
"content": [
{"type": "input_text", "text": (
"Perform RFM customer segmentation: "
"1. Calculate Recency, Frequency, Monetary for each customer "
"2. Assign an RFM score from 1 to 5 for each dimension "
"3. Create segments: Champions, Loyal, At Risk, Lost "
"4. Apply K-Means (k=4 to 8, choose the best k using elbow method) "
"5. Visualize segments in 2D (PCA or t-SNE) "
"6. Profile each segment: size, average revenue, frequency "
"7. Export: CSV with segment per customer + PDF-like report"
)},
{"type": "input_file", "file_id": file_obj.id}
]
}],
tools=[{"type": "code_interpreter", "container": {"type": "auto"}}],
instructions=(
"Use sklearn for clustering. "
"Normalize variables before clustering. "
"Display the elbow plot to justify the choice of k. "
"Create a radar chart per segment."
)
)
output_files = []
for ann in fichiers_generes(response):
telecharger(client, ann, ann.filename)
output_files.append(ann.filename)
return {
"analysis": response.output_text,
"files": output_files
}
Fluss ta’ Ħidma 4: Tbassir u Xejriet
It-tbassir huwa l-fluss ta’ ħidma fejn il-kawtela hija l-aktar importanti. Il-kontenitur jista’ jwettaq rigressjoni jew dekompożizzjoni staġjonali, u jagħmel hekk anke meta d-data tiegħek ma tkunx xierqa—għoxrin punt ta’ data biżżejjed biex jipproduċu kurva perfettament preżentabbli li hija kompletament bla sens. Itlob l-intervall ta’ kunfidenza u s-suppożizzjonijiet tal-mudell: dan huwa dak li jiddistingwi projezzjoni minn estrapolazzjoni.
response = client.responses.create(
model="gpt-5.6-terra",
input=[{
"role": "user",
"content": [
{"type": "input_text", "text": (
"Based on this monthly sales data: "
"1. Decompose the time series (trend, seasonality, residual) "
"2. Apply exponential smoothing (Holt-Winters) "
"3. Forecast the next 6 months with a 95% confidence interval "
"4. Compare with a simple linear regression "
"5. Generate a chart with history + forecasts "
"6. Calculate error metrics (MAE, RMSE, MAPE)"
)},
{"type": "input_file", "file_id": file_obj.id}
]
}],
tools=[{"type": "code_interpreter", "container": {"type": "auto"}}],
instructions=(
"Use statsmodels for decomposition and forecasting. "
"Color the confidence interval in transparent blue. "
"Clearly mark the separation between history and forecasts."
)
)
Orkestrazzjoni ta’ Fluss ta’ Ħidma Multi-Pass
Wara ċerta daqs, prompt wieħed jilħaq il-limiti tiegħu: l-analiżi tiddevja, istruzzjoni intermedjarja tintesa, u titlef il-kont ta’ liema pass qiegħed fih. Il-qsam tal-proċess f’sejħiet suċċessivi, li kollha jaħdmu fl-istess kontenitur fejn il-fajls mill-pass preċedenti jibqgħu disponibbli, jirrestawra dak li tileft—punt ta’ kontroll wara kull pass, u l-kapaċità li terġa’ tibda mill-pass difettuż minflok ma terġa’ tibda kollox.
class WorkflowData:
def __init__(self):
self.client = OpenAI()
# An explicit container: files produced remain available from one step to the next
self.container = self.client.containers.create(name="workflow-data")
self.intermediate_files = []
def step(self, instruction: str, file_ids: list[str] | None = None) -> str:
"""Executes a workflow step in the shared container."""
content = [{"type": "input_text", "text": instruction}]
for fid in file_ids or []:
content.append({"type": "input_file", "file_id": fid})
response = self.client.responses.create(
model="gpt-5.6-terra",
input=[{"role": "user", "content": content}],
tools=[{"type": "code_interpreter", "container": self.container.id}],
)
# Memorize generated files to download at the end
self.intermediate_files.extend(fichiers_generes(response))
return response.output_text
def download_results(self, output_folder: str):
"""Downloads generated files before the container expires."""
import os
os.makedirs(output_folder, exist_ok=True)
for ann in self.intermediate_files:
telecharger(self.client, ann, os.path.join(output_folder, ann.filename))
# Usage
wf = WorkflowData()
# Step 1: Import and clean
with open("donnees_brutes.csv", "rb") as f:
file_obj = client.files.create(file=f, purpose="user_data")
wf.step(
"Clean this CSV: remove duplicates, handle missing values, "
"normalize types. Export the result.",
[file_obj.id]
)
# Step 2: Analysis
wf.step("Calculate key KPIs and identify trends.")
# Step 3: Visualization
wf.step("Create 4 key charts for an executive report.")
# Step 4: Export
wf.step("Compile everything into an Excel file with tabs and embedded charts.")
wf.download_results("./sortie_workflow/")
Punti Ewlenin
- Aqsam flussi ta’ ħidma kumplessi f’passi bil-passaġġ tal-fajls
- Uża istruzzjonijiet dettaljati għal kull pass
- Il-mudell jimmanipola naturalment l-analiżi statistika u t-tagħlim awtomatiku bażiku
- Irkupra sistematikament il-fajls intermedjarji għat-traċċabbiltà
- Għaqqad l-analiżi tad-data u l-viżwalizzazzjoni f’sejħa waħda għal rapporti sħaħ