v1

.idea/.gitignore

+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/profiles_settings.xml

+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (task4)" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file

.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/task4.iml" filepath="$PROJECT_DIR$/.idea/task4.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

.idea/task4.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>
\ No newline at end of file

.idea/vcs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file

app.py

+# Python task 4 pandas and json
+from scripts.services.read_data_chunks import data_chunks
+
+print("This is program is to work with pandas")
+data_chunks()

scripts/core/handlers/col_concat.py

+# concatenate two columns
+import pandas as pd
+
+
+def concat_details(data_details):
+    data_det = data_details
+    full_name = pd.DataFrame()
+    try:
+        for chunks in data_det:
+            full_name_chunks = chunks['first_name'] + " " + chunks['last_name']
+            full_name = pd.concat([full_name, full_name_chunks])
+        full_name.columns = ['full_name']
+        print(full_name.head(10))
+    except Exception as e:
+        print("Exception occurred: ", e)
+    # full_name.to_csv('scripts/utils/user_full_name', index=False)

scripts/services/read_data_chunks.py

+# creating chunks
+import pandas as pd
+
+from scripts.core.handlers.col_concat import concat_details
+
+
+def data_chunks():
+    # chunk size
+    chunk_size = 100
+
+    # columns
+    cols = ['id', 'first_name', 'last_name']
+
+    #  import dataset
+    try:
+        data_details = pd.read_csv("scripts/utils/MOCK_DATA.csv", chunksize=chunk_size, usecols=cols)
+    except Exception as e:
+        print(f'File not found : {e}')
+    else:
+        concat_details(data_details)
+        # loc_iloc_diff(data_details)
+        # col_specific_row(data_details)
\ No newline at end of file