diff --git a/class.py b/class.py
new file mode 100644
index 0000000..4a53b63
--- /dev/null
+++ b/class.py
@@ -0,0 +1,39 @@
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+data = pd.read_csv('works.csv')
+
+# 1
+print(len(data.index))
+print(data.shape[0])
+print(data.info())
+
+# 2
+# print((data['gender']=='Мужской').sum(), (data['gender']=='Женский').sum())
+print(data.gender.value_counts())
+
+# 3
+print(data.info())
+print(data.skills.notna().sum())
+print(data.skills.count())
+
+# 4
+print(data[data.skills.notna()]['skills'])
+print(data.skills.dropna())
+
+# 5
+new_data = data[data.skills.notna()]
+print(new_data[new_data.skills.str.lower().str.contains('python|питон')].salary)
+
+# 6
+index = data.skills.str.lower().str.contains('python|питон')
+mask = index.notna()
+print(data[mask & index].salary)
+
+# 7
+data.query("gender == 'Мужской' and educationType == 'Высшее'").hist(bins=100, alpha=0.5)
+plt.show()
+
+data.query("gender == 'Женский' and educationType == 'Высшее'").hist(bins=100, alpha=0.5)
+plt.show()
\ No newline at end of file
diff --git a/homework.py b/homework.py
new file mode 100644
index 0000000..00e882e
--- /dev/null
+++ b/homework.py
@@ -0,0 +1,37 @@
+import pandas as pd
+
+data = pd.read_csv('works.csv')
+data
+
+data.dropna(subset=['jobTitle'], inplace=True)
+data.dropna(subset=['qualification'], inplace=True)
+
+data.shape[0]
+
+data['qualification'] = data['qualification'].str.replace('-', ' ')
+data["jobTitle"] = data["jobTitle"].str.replace('-', ' ')
+
+# Профессия и должность не совпадают
+(data['jobTitle'] == data['qualification']).value_counts()
+
+def comparison(column1, column2):
+    list1 = column1.split()
+    for word in list1:
+        if word in column2:
+            return True
+    return False
+
+count = 0
+for (job, qualification) in zip(data["jobTitle"], data["qualification"]):
+    if comparison(job, qualification) or comparison(qualification, job):
+        count += 1
+
+data.shape[0] - count
+
+# Топ-5 образовний менеджеров
+managers = data[data["jobTitle"].str.lower().str.contains("менедж")]
+managers['qualification'].str.lower().value_counts().head(5)
+
+# Топ-5 образовний инженеров
+engineers = data[data["qualification"].str.lower().str.contains("инженер")]
+engineers['jobTitle'].str.lower().value_counts().head(5)
\ No newline at end of file