Update README.md
Browse files
README.md
CHANGED
|
@@ -87,13 +87,13 @@ Ensure your project follows this structure:
|
|
| 87 |
β βββ data1.jsonl
|
| 88 |
β βββ data2.jsonl
|
| 89 |
βββ models/
|
| 90 |
-
β βββ model.joblib
|
| 91 |
-
β βββ scaler.pkl
|
| 92 |
-
βββ output/
|
| 93 |
-
βββ dummy.py
|
| 94 |
-
βββ
|
| 95 |
-
βββ
|
| 96 |
-
βββ
|
| 97 |
```
|
| 98 |
|
| 99 |
## 5. Usage
|
|
@@ -110,9 +110,9 @@ The script is configured to run out-of-the-box. Simply place your data files in
|
|
| 110 |
Open your terminal and execute the Python script:
|
| 111 |
|
| 112 |
```bash
|
| 113 |
-
python -W ignore
|
| 114 |
or
|
| 115 |
-
python -W ignore
|
| 116 |
```
|
| 117 |
|
| 118 |
### Step 3: Check the Output
|
|
@@ -127,7 +127,7 @@ The script automatically skips files that have already been processed and exist
|
|
| 127 |
|
| 128 |
```
|
| 129 |
|
| 130 |
-
python -W ignore
|
| 131 |
Znaleziono 1 plikΓ³w w folderze wejΕciowym
|
| 132 |
input_parquet\docs.parquet
|
| 133 |
|
|
|
|
| 87 |
β βββ data1.jsonl
|
| 88 |
β βββ data2.jsonl
|
| 89 |
βββ models/
|
| 90 |
+
β βββ model.joblib # The trained XGBoost model
|
| 91 |
+
β βββ scaler.pkl # The scikit-learn scaler
|
| 92 |
+
βββ output/ # Output directory for processed files
|
| 93 |
+
βββ dummy.py # The interactive testing script
|
| 94 |
+
βββ main_jsonl.py # The main processing script jsonl
|
| 95 |
+
βββ main_parquet.py # The main processing script parquet
|
| 96 |
+
βββ predictor.py # The feature extraction module
|
| 97 |
```
|
| 98 |
|
| 99 |
## 5. Usage
|
|
|
|
| 110 |
Open your terminal and execute the Python script:
|
| 111 |
|
| 112 |
```bash
|
| 113 |
+
python -W ignore main_jsonl.py
|
| 114 |
or
|
| 115 |
+
python -W ignore main_parquet.py
|
| 116 |
```
|
| 117 |
|
| 118 |
### Step 3: Check the Output
|
|
|
|
| 127 |
|
| 128 |
```
|
| 129 |
|
| 130 |
+
python -W ignore main_parquet.py
|
| 131 |
Znaleziono 1 plikΓ³w w folderze wejΕciowym
|
| 132 |
input_parquet\docs.parquet
|
| 133 |
|