done part 4

out/doc2vec_prec_recall.txt

@@ -0,0 +1,2 @@
+Precision: 30.00%
+Recall: 30.00%

out/freq_prec_recall.txt

@@ -0,0 +1,2 @@
+Precision: 24.50%
+Recall: 24.50%

out/lsi_prec_recall.txt

@@ -0,0 +1,2 @@
+Precision: 3.33%
+Recall: 3.33%

out/tfidf_prec_recall.txt

@@ -0,0 +1,2 @@
+Precision: 22.50%
+Recall: 22.50%

prec-recall.py

@@ -1,4 +1,5 @@
 import argparse
+import os.path
 from typing import Iterable, Optional
 
 import numpy as np
@@ -10,7 +11,8 @@ from sklearn.manifold import TSNE
 
 search_data = __import__('search-data')
 
-PREFIX: str = "./"
+TENSORFLOW_PATH_PREFIX: str = "./"
+OUT_DIR: str = os.path.join(os.path.dirname(__file__), "out")
 
 
 def read_ground_truth(file_path: str, df: pd.DataFrame) -> Iterable[tuple[str, int]]:
@@ -31,8 +33,8 @@ def read_ground_truth(file_path: str, df: pd.DataFrame) -> Iterable[tuple[str, i
         records.append(record_tmp)
 
     for query, name, file_name in records:
-        assert file_name.startswith(PREFIX)
+        assert file_name.startswith(TENSORFLOW_PATH_PREFIX)
-        file_name = file_name[len(PREFIX):]
+        file_name = file_name[len(TENSORFLOW_PATH_PREFIX):]
 
         row = df[(df.name == name) & (df.file == file_name)]
         assert len(row) == 1
@@ -51,14 +53,13 @@ def better_index(li: list[tuple[int, float]], e: int) -> Optional[int]:
 def plot_df(results, query: str) -> Optional[pd.DataFrame]:
     if results.vectors is not None and results.query_vector is not None:
         tsne_vectors = np.array(results.vectors + [results.query_vector])
-        # try perplexity = 1, 1.5, 2
         tsne = TSNE(n_components=2, verbose=1, perplexity=1.5, n_iter=3000)
         tsne_results = tsne.fit_transform(tsne_vectors)
-        df = pd.DataFrame(columns=['tsne-2d-one', 'tsne-2d-two',  'query', 'is_input'])
+        df = pd.DataFrame(columns=['tsne-2d-one', 'tsne-2d-two', 'Query', 'Vector kind'])
         df['tsne-2d-one'] = tsne_results[:, 0]
         df['tsne-2d-two'] = tsne_results[:, 1]
-        df['query'] = [query] * (len(results.vectors) + 1)
+        df['Query'] = [query] * (len(results.vectors) + 1)
-        df['is_input'] = (['Result'] * len(results.vectors)) + ['Input query']
+        df['Vector kind'] = (['Result'] * len(results.vectors)) + ['Input query']
         return df
     else:
         return None
@@ -92,22 +93,28 @@ def main(method: str, file_path: str):
         precision_sum += precision
         recall_sum += recall
 
-    print("Precision: {0:.2f}%".format(precision_sum * 100 / len(test_set)))
+    if not os.path.isdir(OUT_DIR):
-    print("Recall: {0:.2f}%".format(recall_sum * 100 / len(test_set)))
+        os.makedirs(OUT_DIR)
 
-    df = pd.concat(dfs)
+    output = "Precision: {0:.2f}%\nRecall: {0:.2f}%\n".format(precision_sum * 100 / len(test_set))
 
-    plt.figure(figsize=(4, 4))
+    print(output)
-    ax = sns.scatterplot(
+    with open(os.path.join(OUT_DIR, "{0}_prec_recall.txt".format(method)), "w") as f:
-        x="tsne-2d-one", y="tsne-2d-two",
+        f.write(output)
-        hue="query",
+
-        style="is_input",
+    if len(dfs) > 0:
-        palette=sns.color_palette("husl", n_colors=10),
+        df = pd.concat(dfs)
-        data=df,
+        plt.figure(figsize=(20, 16))
-        legend="full",
+        sns.scatterplot(
-        alpha=1.0
+            x="tsne-2d-one", y="tsne-2d-two",
-    )
+            hue="Query",
-    plt.show()
+            style="Vector kind",
+            palette=sns.color_palette("husl", n_colors=10),
+            data=df,
+            legend="full",
+            alpha=1.0
+        )
+        plt.savefig(os.path.join(OUT_DIR, "{0}_plot.png".format(method)))
 
 
 if __name__ == '__main__':