From 0577f982a26e2f4a1516720c22d201e6fa8d1776 Mon Sep 17 00:00:00 2001
From: Pavan Mandava <mspavan04@gmail.com>
Date: Sun, 10 May 2020 18:05:25 +0200
Subject: [PATCH] Reading Train file done, fixed os path issues

---
 testing/eval_testing.py | 12 ++++++++++++
 utils/csv.py            | 19 +++++++++++++++++++
 utils/models.py         | 13 +++++++++++++
 3 files changed, 44 insertions(+)
 create mode 100644 utils/models.py

diff --git a/testing/eval_testing.py b/testing/eval_testing.py
index acf2c7d..b4353ef 100644
--- a/testing/eval_testing.py
+++ b/testing/eval_testing.py
@@ -1,6 +1,8 @@
 from eval.metrics import f1_score
 import utils.constants as const
 from sklearn.metrics import f1_score as f1
+import os
+from utils.csv import read_csv_file
 
 y_true = ['positive', 'positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative']
 y_pred = ['positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative', 'positive', 'positive', 'negative', 'negative', 'negative']
@@ -18,3 +20,13 @@ for result in result_list:
     result.print_result()
 
 print('SK Learn F1 Score (MACRO):: ', f1(y_true, y_pred, ['positive', 'negative'], average='macro'))
+
+
+project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+train_file_path = project_root+'/data/tsv/train.tsv'
+print(train_file_path)
+
+data = read_csv_file(csv_file_path=train_file_path, delimiter='\t')
+for inst in data[:5]:
+    inst.print()
diff --git a/utils/csv.py b/utils/csv.py
index e69de29..51b32c2 100644
--- a/utils/csv.py
+++ b/utils/csv.py
@@ -0,0 +1,19 @@
+import csv
+from utils.models import DataInstance
+
+
+def read_csv_file(csv_file_path, delimiter='\t'):
+    """
+     This function takes file path as an argument, reads the data file and
+     returns a list of DataInstance objects with text and true labels
+
+    :param delimiter: Delimiter for the file. Default is Tab(\t)
+    :param csv_file_path: path to the TSV/CSV file
+    :return: returns a list of  DataInstance class objects. <utils.models.DataInstance>
+    """
+    with open(csv_file_path, 'r') as file:
+        file_data = csv.reader(file, delimiter=delimiter)
+        data = []
+        for row in file_data:
+            data.append(DataInstance(row[0], row[2], row[3]))
+        return data
diff --git a/utils/models.py b/utils/models.py
new file mode 100644
index 0000000..f2a6753
--- /dev/null
+++ b/utils/models.py
@@ -0,0 +1,13 @@
+
+class DataInstance:
+    """
+    Model Class for carrying Training and Testing data from tsc/csv file
+    """
+
+    def __init__(self, r_id, text, true_label):
+        self.did = r_id
+        self.text = text
+        self.true_label = true_label
+
+    def print(self):
+        print('True Label :: ', self.true_label, ' Text :: ', self.text)