Skip to content
Snippets Groups Projects
Commit 946d9cf4 authored by Franziska Niemeyer's avatar Franziska Niemeyer
Browse files

Upload solutions for exercises_E

parent d1a36317
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
Exercises/solutions/Python_course_2021_exercises_E.ipynb 0 → 100644
+ 323
− 0
View file @ 946d9cf4
%% Cell type:markdown id: tags:
# Python course 2021 - Exercises E
%% Cell type:code id: tags:
```
from google.colab import drive
drive.mount('/content/drive')
```
%% Output
Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).
%% Cell type:markdown id: tags:
## Part1 - modules
%% Cell type:markdown id: tags:
---
1.1) Write all AGIs of AtCol0_exons.fasta into a new file!
%% Cell type:code id: tags:
```
def get_gene_identifiers(input, output):
with open(input, 'r') as input_file:
with open(output, 'w') as output_file:
for line in input_file:
if line.startswith(">"):
identifier = line[1:].split(".")[0]
output_file.write(identifier + "\n")
input = "/content/drive/MyDrive/PythonProgramming/AtCol0_Exons.fasta"
output = "/content/drive/MyDrive/PythonProgramming/AtCol0_gene_identifiers.txt"
get_gene_identifiers(input, output)
def get_num_lines(input):
num_lines = 0
with open(input, 'r') as input_file:
for line in input_file:
num_lines += 1
return num_lines
print(get_num_lines("/content/drive/MyDrive/PythonProgramming/AtCol0_gene_identifiers.txt"))
```
%% Output
217183
%% Cell type:markdown id: tags:
---
1.2) Some IDs occur multiple times. Add a filter step to reduce the results to unique IDs!
%% Cell type:code id: tags:
```
def get_unique_gene_identifiers(input, output):
# use the built-in set data structure
identifier_set = set()
with open(input, 'r') as input_file:
for line in input_file:
if line.startswith(">"):
identifier = line[1:].split(".")[0]
identifier_set.add(identifier)
with open(output, 'w') as output_file:
for identifier in identifier_set:
output_file.write(identifier + "\n")
output = "/content/drive/MyDrive/PythonProgramming/AtCol0_unique_gene_identifiers.txt"
get_unique_gene_identifiers(input, output)
get_num_lines("/content/drive/MyDrive/PythonProgramming/AtCol0_unique_gene_identifiers.txt")
```
%% Output
33602
%% Cell type:markdown id: tags:
---
1.3) Calculate the frequency of each AGI and construct a histogram (matplotlib)!
```
plt.hist(<list_of_values>) #tip
```
%% Cell type:code id: tags:
```
import matplotlib.pyplot as plt
def get_identifier_frequencies(input):
# use a dictionary to keep track of the number of occurrences of each identifier
identifier_occurrences = {}
with open(input, 'r') as input_file:
for line in input_file:
if line.startswith(">"):
identifier = line[1:].split(".")[0]
identifier_occurrences[identifier] = identifier_occurrences.setdefault(identifier, 0) + 1
return identifier_occurrences
def plot_frequency_histogram(input, output):
identifier_occurrences = get_identifier_frequencies(input)
fig, ax = plt.subplots(constrained_layout=True, dpi=200)
ax.hist(identifier_occurrences.values(), bins=range(max(identifier_occurrences.values()) + 1))
ax.set_xlabel("Number of occurrences")
ax.set_ylabel("Number of unique identifiers")
ax.set_title("AGI frequency histogram")
fig.savefig(output)
plot_frequency_histogram(input, "/content/drive/MyDrive/PythonProgramming/AtCol0_identifier_frequency_histogram.png")
```
%% Output
%% Cell type:markdown id: tags:
**Additional exercises**
%% Cell type:markdown id: tags:
1.4) Create a bar chart with matplotlib that shows the frequencies of the five most common AGIs.
%% Cell type:code id: tags:
```
from heapq import nlargest
"""
Finds the k most frequent gene identifiers.
"""
def get_most_frequent_gene_identifiers(identifier_occurrences, k):
most_frequent_identifiers = nlargest(k, identifier_occurrences.keys(), key=lambda identifier: identifier_occurrences[identifier])
frequencies = []
for identifier in most_frequent_identifiers:
frequencies += [identifier_occurrences[identifier]]
return most_frequent_identifiers, frequencies
"""
Create a bar plot for the k most frequent gene identifiers.
"""
def plot_most_frequent_identifiers(input, output, k):
identifiers, frequencies = get_most_frequent_gene_identifiers(get_identifier_frequencies(input), k)
fig, ax = plt.subplots(constrained_layout=True, dpi=200)
ax.bar(range(len(identifiers)), frequencies, tick_label=identifiers)
ax.set_xlabel("Gene identifier")
ax.set_ylabel("Number of occurrences")
ax.set_title(f"{k} most frequent gene identifiers")
fig.savefig(output)
get_most_frequent_gene_identifiers(get_identifier_frequencies(input), 5)
plot_most_frequent_identifiers(input, "/content/drive/MyDrive/PythonProgramming/AtCol0_most_frequent_identifiers_bar_plot.png", 5)
```
%% Output
%% Cell type:code id: tags:
```
```
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment