diff --git a/homework_task.py b/homework_task.py
new file mode 100644
index 0000000..cd7a4cd
--- /dev/null
+++ b/homework_task.py
@@ -0,0 +1,29 @@
+#task8
+import pandas
+import numpy
+import matplotlib.pyplot as plt
+
+works = pandas.read_csv("works.csv").dropna()
+def count(field1, field2, works):
+    result = 0
+    for f1, f2 in zip(works[field1], works[field2]):
+        if not match(f1, f2) and not match(f2, f1):
+            result += 1
+    return result
+
+def match(f1, f2):
+    array = f1.lower().replace('-', ' ').split()
+    for word in array:
+        if word in f2.lower():
+            return True
+    return False
+
+
+result = count("jobTitle", "qualification", works)
+print("Из {} людей не совпадают профессия и должность у {}".format(works.shape[0], result))
+
+print("\nТоп образований людей для менеджеров")
+print(works[works['jobTitle'].str.lower().str.contains('менеджер'[:-2])]['qualification'].str.lower().value_counts().head(5))
+
+print("\nТоп должностей людей, которые по диплому являются инженерами")
+print(works[works['jobTitle'].str.lower().str.contains('инженер'[:-2])]['qualification'].str.lower().value_counts().head(5))
\ No newline at end of file
diff --git a/report.md b/report.md
new file mode 100644
index 0000000..1a450b4
--- /dev/null
+++ b/report.md
@@ -0,0 +1,13 @@
+1.Профессия и должность не совпадают у 793 человек.
+2.Топ-5 образований для менеджеров: 
+бакалавр 11 
+менеджер 10 
+специалист 6 
+экономист 6
+экономист-менеджер 4
+Топ-5 профессий людей, получивших диплом инженера: 
+заместитель директора 3 
+главный инженер 3 
+ведущий инженер-конструктор 2 
+инженер лесопользования 2 
+директор 2
\ No newline at end of file
diff --git a/task.py b/task.py
new file mode 100644
index 0000000..06d2ca4
--- /dev/null
+++ b/task.py
@@ -0,0 +1,75 @@
+import pandas
+import numpy
+import matplotlib.pyplot as plt
+
+works = pandas.read_csv("works.csv")
+print(works['skills'].str.lower().str.contains('python|питон'))
+
+#task1
+works = pandas.read_csv("works.csv")
+head = works.head(5)
+print(head)
+
+tail = works.tail(5)
+print(tail)
+print(works.shape[0])
+print(len(works.index))
+
+#task2
+print(works[works['gender'] == 'Мужской'].shape[0])
+print((works['gender'] == 'Женский').sum())
+print(works['gender'].value_counts())
+
+#task3
+print(works['skills'].notnull().sum())
+print(works.info())
+print(works['skills'].count())
+
+#task4
+print(works[works['skills'].notnull()]['skills'])
+print(works['skills'].dropna())
+print(works.query("skills == skills")["skills"])
+print(works.query("salary == 15000"))
+edu = 'Высшее'
+gen = 'Женский'
+print(works.query("educationType == @edu and gender == @gen")[['salary', 'educationType','gender']])
+
+#task5
+mask = works["skills"].str.lower().str.contains("python|питон") & works["skills"].notnull()
+print(works[mask]["salary"])
+
+#task6
+percentiles = numpy.linspace(.1, 1, 10)
+
+gen = "Мужской"
+men_salary = works.query('gender == @gen').quantile(percentiles)
+fig, ax = plt.subplots()
+ax.plot(percentiles, men_salary)
+plt.xlabel('Перцентили')
+plt.ylabel('Зарплата мужчин')
+plt.show()
+
+gen = "Женский"
+women_salary = works.query('gender == @gen').quantile(percentiles)
+fig, ax = plt.subplots()
+ax.plot(percentiles, women_salary)
+plt.xlabel('Перцентили')
+plt.ylabel('Зарплата женщин')
+plt.show()
+
+#task7
+gen = "Мужской"
+men_salary = works.query('gender == @gen').groupby("educationType").agg("mean").reset_index()
+men = men_salary['salary'].values
+gen = "Женский"
+women_salary = works.query('gender == @gen').groupby("educationType").agg("mean").reset_index()
+women = women_salary['salary'].values
+
+types = men_salary["educationType"].values
+id = numpy.arange(len(types))
+
+plt.bar(id - 0.2, men, 0.4, color="g", label = "Средняя зарплата мужчин")
+plt.bar(id + 0.2, women, 0.4, color="y", label = "Средняя зарплата женщин")
+plt.xticks(id, types, rotation=45)
+plt.legend()
+plt.show()
\ No newline at end of file