Skip to content

Commit 978757c

Browse files
rphadtarerphadtare
committed
2024/03/29 - Updating Demo python files
1 parent e446d13 commit 978757c

File tree

3 files changed

+270
-4
lines changed

3 files changed

+270
-4
lines changed

‎advanced/PythonDemo_03_Numpy_module.py‎

Lines changed: 13 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44

55

66
def initialisation_demo():
7-
# To create empty array
7+
"""To create empty array using built in methods"""
88
arr = np.zeros(5, 'i')
99
print("Empty arr: ", arr, " dtype:", arr.dtype, " dimension: ", arr.ndim)
1010

@@ -31,6 +31,7 @@ def initialisation_demo():
3131

3232

3333
def one_dimensional_array():
34+
"""Demo functionality for index and slicing operations on one-d array"""
3435
num_list = random.sample(range(0, 100), 7)
3536
arr = np.array(num_list, 'i')
3637
print("Accessing elements using indexing of one dimensional array")
@@ -57,7 +58,7 @@ def one_dimensional_array():
5758

5859

5960
def two_dimensional_arr():
60-
# empty array with zero values
61+
"""Demo functionality for index and slicing operations on 2-d array"""
6162
arr = np.zeros((2, 2), dtype='i')
6263
print("2-D array with zero values ", arr)
6364

@@ -98,6 +99,7 @@ def two_dimensional_arr():
9899

99100

100101
def copy_and_view_demo():
102+
"""Demo functionality of copy and view methods from numpy module"""
101103
arr = np.array([1, 2, 3, 4], dtype=int)
102104
print("Original arr : ", arr, " base: ", arr.base)
103105
arr1 = arr.copy()
@@ -119,6 +121,7 @@ def copy_and_view_demo():
119121

120122

121123
def shapeDemo():
124+
"""Demo functionality to understand shape of numpy module"""
122125
arr = np.full((3, 2), 1, dtype='i')
123126
for i in arr:
124127
for j in i:
@@ -127,13 +130,16 @@ def shapeDemo():
127130

128131

129132
def reShapeDemo():
133+
"""Demo functionality to understand reshape and resize of numpy module"""
130134

131135
num_list = random.sample(range(1, 100), 7)
132136
arr = np.array(num_list, dtype='i')
133137
print(f"Input array before resize: {arr} with shape: {arr.shape} and base: {arr.base}")
138+
reshaped_arr = None
134139

135140
try:
136141
reshaped_arr = np.reshape(arr, newshape=(2, 4))
142+
print(f"Reshaped array with new shape: {reshaped_arr.shape} and base: {reshaped_arr.base}")
137143

138144
except ValueError as v:
139145
print("Error received : ", v)
@@ -153,6 +159,7 @@ def reShapeDemo():
153159
print("-"*50)
154160

155161
def reShapeDemo2():
162+
"""Demo functionality to understand flatten and ravel of numpy module"""
156163
arr = np.array([[1, 2, 3], [4, 5, 6]], dtype='i')
157164
print(f"Input array before reshape: {arr} with shape: {arr.shape} and base: {arr.base}")
158165
arr1 = arr.flatten()
@@ -162,11 +169,14 @@ def reShapeDemo2():
162169

163170

164171
def itrDemo():
172+
"""Demo functionality to understand nditer() method"""
165173
arr = np.array([[1, 2, 3], [4, 5, 6]], dtype='i')
166174
for x in np.nditer(arr[::, :2], flags=['buffered'], op_dtypes='S'):
167175
print(x)
168176

169177
def joinDemo():
178+
"""Demo functionality to understand joining of array from numpy module"""
179+
170180
arr1 = np.array([1, 2, 3, 4, 5], dtype='i')
171181
arr2 = np.array([7, 8, 9, 10, 11], dtype='i')
172182

@@ -182,6 +192,7 @@ def joinDemo():
182192
# using vstack
183193
print(np.vstack((arr1, arr2)))
184194

195+
185196
def main():
186197
print("Version of numpy", np.__version__)
187198
reShapeDemo()

‎advanced/PythonDemo_04_Random_module.py‎

Lines changed: 11 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,13 +3,16 @@
33

44

55
def generateRandomNumbers():
6+
"""Function to understand how to generate single random int or float"""
67
print("Random int: ", random.randint(0, 10))
78
print("Random float between 0 and 1: ", random.rand())
89
print("Random float between 10 and 20: ", random.uniform(10, 20))
910
print("-" * 25)
1011

1112

1213
def generateRandomArrays():
14+
"""Function to understand how to generate 1-d array of random int or float"""
15+
1316
print("One Dimensional array")
1417
print("Random int array: ", random.randint(low=5, high=12, size=5))
1518
print("Random float array: ", random.rand(3))
@@ -18,6 +21,8 @@ def generateRandomArrays():
1821

1922

2023
def generateRandomArrays2():
24+
"""Function to understand how to generate 1-d array of random int or float"""
25+
2126
print("Two Dimensional array")
2227
print("Random int array: ", random.randint(low=5, high=12, size=(2, 3)))
2328
print("Random float array: ", random.rand(3, 2))
@@ -26,13 +31,18 @@ def generateRandomArrays2():
2631

2732

2833
def generateRandomArraysWithChoice():
34+
"""Function to understand how to generate 1-d array of random int or float with choice function"""
35+
2936
print("generateRandomArraysWithChoice")
3037
print("Random int array with choice : ", random.choice([10, 20, 30, 40, 11], 3))
3138
print("Random int array with choice and probability: ", random.choice([10, 20, 30], 6, p=[0.25, 0.45, 0.30]))
3239
print("Random float array with choice : ", random.choice([10.5, 12.0, 11.25, 31.5], 3))
3340
print("-" * 25)
3441

42+
3543
def shuffle_and_permutation_demo():
44+
"""Function to understand shuffle and permutation functions from random module"""
45+
3646
arr = np.array([1, 2, 3, 4, 5])
3747
print("Array before shuffling: ", arr)
3848
random.shuffle(arr)
@@ -46,8 +56,6 @@ def shuffle_and_permutation_demo():
4656
print("-" * 25)
4757

4858

49-
50-
5159
def main():
5260
print("Version of numpy", np.__version__)
5361
generateRandomNumbers()
@@ -56,5 +64,6 @@ def main():
5664
generateRandomArraysWithChoice()
5765
shuffle_and_permutation_demo()
5866

67+
5968
if __name__ == "__main__":
6069
main()

‎advanced/PythonDemo_05_Pandas_module.py‎

Lines changed: 246 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,246 @@
1+
# This file provides demo for pandas functionality
2+
import random
3+
4+
import pandas as pd
5+
6+
7+
def seriesDemo():
8+
"""This function gives demo for Pandas Series"""
9+
a = [1, 2.2, "Pooja", 4, 5]
10+
s1 = pd.Series(a, index=["id", "module_num", "name", "n1", "n2"])
11+
print("Series before update\n", s1)
12+
s1.loc[0] = 2
13+
s1.iloc[3:5] = 12
14+
s1._set_value("n1", 15)
15+
s1['name'] = 'Mrs. Pooja'
16+
print("Series before update")
17+
print(s1)
18+
19+
d1 = {'c1': 'India', 'c2': 'USA', 'c3': 'Switzerland'}
20+
print("Dictionary: ", d1)
21+
s2 = pd.Series(d1, name='Country')
22+
print(f"Series: {s2.name} Data Type: {s2.dtype} Size: {s2.size} \n")
23+
print(s2)
24+
25+
arr = [1, 2, 3, 4]
26+
arr2 = [10, 20, 30, 4]
27+
s3 = pd.Series(arr)
28+
s4 = pd.Series(arr2)
29+
s5 = pd.concat([s3, s4], ignore_index=True)
30+
s5.name = "S5"
31+
print(s5.drop(labels=2))
32+
print("Index where value 4 is present : \n ", s5.loc[s5 == 4])
33+
34+
35+
def dataFrameDemo():
36+
d1 = {
37+
"id": [1, 2, 3],
38+
"name": ["Rohit", "Pooja", "Rajani"]
39+
}
40+
print(f"Type of d1: {type(d1)}")
41+
df = pd.DataFrame(d1)
42+
print(df)
43+
print("-" * 25)
44+
45+
d2 = [10, 20, 30, 40]
46+
df2 = pd.DataFrame(d2, index=['first', 'second', 'third', 'fourth'], columns=['id'])
47+
print("using iloc with index \n", df2.iloc[1])
48+
print("using loc with label index \n", df2.loc['fourth'])
49+
print("/" * 15)
50+
51+
print("using iloc with multiple rows \n", df2.iloc[[0, 2]])
52+
print("using loc with multiple rows \n", df2.loc[['second', 'fourth']])
53+
print("/" * 15)
54+
55+
print("using iloc slicing \n", df2.iloc[:2])
56+
print("using loc slicing \n", df2.loc['third':'fourth'])
57+
print("-" * 25)
58+
59+
d3 = [random.randint(i, i * 10) for i in range(0, 500)]
60+
d4 = ['A', 'B', 'C', 'D', 'E'] * 100
61+
62+
s3, s4 = pd.Series(d3), pd.Series(d4)
63+
64+
df1 = pd.concat([s3, s4], axis=1).rename(columns={0: 'id', 1: 'str_val'})
65+
print(df1[['id', 'str_val']][10:20])
66+
print("-" * 25)
67+
68+
69+
def dataframe_filter_demo():
70+
"""Dataframe operation"""
71+
72+
d3 = [random.randint(i, i * 10) for i in range(0, 500)]
73+
d4 = ['A', 'B', 'C', 'D', 'E'] * 100
74+
75+
s3, s4 = pd.Series(d3), pd.Series(d4)
76+
77+
df1 = pd.concat([s3, s4], axis=1).rename(columns={0: 'id', 1: 'str_val'})
78+
79+
for x in df1.index:
80+
if df1.loc[x, 'id'] % 500 == 0:
81+
print(df1.loc[x]['id'])
82+
83+
print("Single column condition: \n", df1.loc[df1['str_val'] == 'A'])
84+
print("-" * 25)
85+
86+
print("Double column condition: \n", df1.loc[(df1['str_val'] == 'A') & (df1['id'] % 10 == 0)])
87+
print("-" * 25)
88+
89+
print(df1.query("str_val == 'B' and (id > 110 and id < 700)"))
90+
91+
print(df1.filter(items=['id', 'str_val']).head(20))
92+
93+
print(df1.filter(like='val').head(20))
94+
95+
96+
def dataframe_duplicate_demo():
97+
d = {
98+
'id': [1, 2, 3, 4, 5, 1],
99+
'name': ['R', 'O', 'H', 'I', 'T', 'R']
100+
}
101+
df = pd.DataFrame(d)
102+
print("Input data frame: ", df)
103+
104+
duplicated_series = df.duplicated()
105+
106+
print("Find duplicate rows \n", duplicated_series)
107+
108+
print("Find only duplicated row \n", df[duplicated_series == 1])
109+
110+
print("Remove duplicate rows \n", df.drop_duplicates())
111+
112+
print("Remove duplicate on basis of column values \n", df.drop_duplicates(subset=['name']))
113+
114+
print("update duplicated values in df")
115+
for i in df[duplicated_series == 1].index.values:
116+
df.loc[i] = (6, 'P')
117+
118+
print(df)
119+
120+
121+
def null_handling_demo():
122+
d = {
123+
'id': [1, 2, 3, 4, 5, None, 8],
124+
'name': ['R', 'O', 'H', 'I', 'T', 'C', None]
125+
}
126+
df = pd.DataFrame(d)
127+
128+
print("Data frame with null")
129+
print(df.isna())
130+
131+
print("Remove null values from data frame")
132+
df1 = df.dropna()
133+
df2 = pd.concat([pd.to_numeric(df1['id'], downcast="integer"), df1['name']], axis=1)
134+
print(df2)
135+
136+
print("Fill null values from data frame")
137+
d1 = {'id': 0, 'name': '#'}
138+
df1 = df.fillna(d1).astype(dtype={'id': int, 'name': object})
139+
print(df1)
140+
141+
142+
def dataframe_add_rows():
143+
d = {
144+
'id': [1, 2, 3, 4, 5],
145+
'name': ['R', 'O', 'H', 'I', 'T']
146+
}
147+
df = pd.DataFrame(d)
148+
149+
# to add single row
150+
df.loc[df.index.max() + 1] = (6, 'P')
151+
152+
# to add multiple rows
153+
multiple_rows = {
154+
'id': [7, 8, 9, 10, 11, 12],
155+
'name': ['R', 'A', 'K', 'A', 'S', 'H']
156+
}
157+
df1 = pd.DataFrame(multiple_rows)
158+
df = pd.concat([df, df1], axis=0, ignore_index=True)
159+
print(df)
160+
161+
162+
def dataframe_where_demo():
163+
d = {
164+
'id': [1, 2, 3, 4, 5],
165+
'name': ['R', 'O', 'H', 'I', 'T']
166+
}
167+
df = pd.DataFrame(d)
168+
169+
cond1 = df['id'] > 2
170+
cond2 = df['name'] != 'T'
171+
172+
print(df.where(cond1 & cond2))
173+
174+
175+
def dataframe_remove_rows():
176+
d = {
177+
'id': [1, 2, 3, 4, 5],
178+
'name': ['R', 'O', 'H', 'I', 'T']
179+
}
180+
df = pd.DataFrame(d)
181+
182+
index_list = df.index.values
183+
184+
print("Remove first two elements from dataframe using indexes")
185+
print(df.drop(index=index_list[:2]))
186+
187+
print("Remove elements from dataframe on basis of condition")
188+
df.drop(df[df['id'] == 2].index.values, inplace=True)
189+
print(df)
190+
191+
print("Remove column id from dataframe")
192+
df.drop(columns=['id'], inplace=True)
193+
194+
print(df)
195+
196+
197+
def dataframe_join_demo():
198+
emp_data = {
199+
'emp_id': [10, 20, 30, 40, 50, 60],
200+
'emp_name': ["Rohit", "Pooja", "Rajani", "Rushi", "Rutu", "Prithvi"],
201+
'emp_sal': [5600, 6200, 7900, 7623.45, 5823.41, 5399.14],
202+
'dept_id': [1, 2, 3, 1, 3, 3]
203+
}
204+
205+
dept_data = {
206+
'dept_id': [1, 2, 3],
207+
'dept_name': ["IT", "Civil", "Computer Science"]
208+
}
209+
210+
emp_df = pd.DataFrame(emp_data)
211+
dept_df = pd.DataFrame(dept_data)
212+
print("Emp df \n", emp_df)
213+
print("Dept df \n", dept_df)
214+
215+
print("Joined df")
216+
print(emp_df.join(dept_df.set_index('dept_id'), on='dept_id', how='inner'))
217+
218+
dept_renamed_df = dept_df.rename(columns={'dept_id': 'id'})
219+
print(dept_renamed_df)
220+
# print(emp_df.join(dept_renamed_df.set_index('id'), on='id', how='inner'))
221+
222+
223+
def dataframe_merge_demo():
224+
emp_data = {
225+
'emp_id': [10, 20, 30, 40, 50, 60],
226+
'emp_name': ["Rohit", "Pooja", "Rajani", "Rushi", "Rutu", "Prithvi"],
227+
'emp_sal': [5600, 6200, 7900, 7623.45, 5823.41, 5399.14],
228+
'dept_id': [1, 2, 3, 1, 3, 3]
229+
}
230+
231+
dept_data = {
232+
'id': [1, 2, 3],
233+
'dept_name': ["IT", "Civil", "Computer Science"]
234+
}
235+
236+
emp_df = pd.DataFrame(emp_data)
237+
dept_df = pd.DataFrame(dept_data)
238+
239+
print("Merged df when column name is not same")
240+
print(emp_df.merge(dept_df, how='left', left_on='dept_id', right_on='id'))
241+
242+
print("Merged df when column names are same")
243+
print(emp_df.merge(dept_df.rename(columns={'id': 'dept_id'}), how='left'))
244+
245+
246+
dataframe_remove_rows()

0 commit comments

Comments
 (0)