القائمة
Transform forecasting target to next/current ratio minus one so that optimizing MAE or squared error implicitly minimizes SMAPE
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Memory-efficient Keras generator that streams sharded CSV files in chunks, renders strokes to images on-the-fly, and yields batches for training on datasets too large for memory
Stack 1D convolutions for local feature extraction before bidirectional LSTMs to classify variable-length stroke sequences into hundreds of doodle categories
Partition a large dataset into N balanced shards using integer key modulo arithmetic for reproducible, class-interleaved splits across CSV files
Normalize raw stroke coordinates to 0-255 range, resample at uniform arc-length spacing, then apply Ramer-Douglas-Peucker simplification
Render stroke sequences to grayscale images with temporal intensity encoding where earlier strokes are brighter and later strokes fade to encode drawing order
Score each face in a video as anomalous by computing L2 distance from the embedding centroid of all faces, then convert to probability via logistic function
| name | timeseries-ratio-target-for-smape |
| description | Transform forecasting target to next/current ratio minus one so that optimizing MAE or squared error implicitly minimizes SMAPE |
When the evaluation metric is SMAPE, predicting absolute values penalizes errors asymmetrically. Transforming the target to y_{t+1}/y_t - 1 (the relative change) aligns standard regression losses with SMAPE's symmetric percentage nature. The model learns relative changes, then predictions are converted back via pred * last_known_value + last_known_value.
import pandas as pd
df = df.sort_values(["entity_id", "date"])
df["target_ratio"] = df.groupby("entity_id")["value"].transform(
lambda s: s.shift(-1) / s - 1
)
# Train model on target_ratio with standard MAE/MSE loss
# At inference:
last_known = df.groupby("entity_id")["value"].last()
df["prediction"] = last_known * (1 + predicted_ratio)
value_{t+1} / value_t - 1 as the training target