Tried to read csv files

Blogpost_IRIS/FindFaultyLines.py

@@ -0,0 +1,19 @@
+import pandas as pd
+
+filename = 'C:/Users/SPECTRE/anaconda3/blog.datathinking.org/Blogpost_IRIS/final_file_PAT_Res.csv' 
+error_lines = []
+
+with open(filename, 'r') as file:
+    for line_number, line in enumerate(file, start=1):
+        line = line.strip()
+        columns = line.split(',')
+        num_values = len(columns)
+        if num_values != 69:  # Adjust the expected number of columns accordingly
+            error_lines.append((line_number, num_values))
+
+print(f"Found {len(error_lines)} lines with inconsistent column count:")
+for line_number, num_values in error_lines:
+    print(f"Line {line_number}: {num_values} values")
+
+
+

Blogpost_IRIS/Fix_columnnames.py

@@ -0,0 +1,38 @@
+import pandas as pd
+from tabulate import tabulate
+
+# Load the final file
+df = pd.read_csv('final_file.csv')
+
+# Add a new index column
+#df['New Index'] = range(1, len(df) + 1)
+
+# Specify the range of rows and columns you want to display
+#subset = df.iloc[:10, :5]
+
+# Convert the subset to a formatted table
+#table = tabulate(subset, headers='keys', tablefmt='psql')
+
+# Original column names
+column_names = ['Country Name', 'Country Code', 'Indicator Name', 'Indicator Code',
+       '1960', '1961', '1962', '1963', '1964', '1965', '1966', '1967', '1968',
+       '1969', '1970', '1971', '1972', '1973', '1974', '1975', '1976', '1977',
+       '1978', '1979', '1980', '1981', '1982', '1983', '1984', '1985', '1986',
+       '1987', '1988', '1989', '1990', '1991', '1992', '1993', '1994', '1995',
+       '1996', '1997', '1998', '1999', '2000', '2001', '2002', '2003', '2004',
+       '2005', '2006', '2007', '2008', '2009', '2010', '2011', '2012', '2013',
+       '2014', '2015', '2016', '2017', '2018', '2019', '2020', '2021', '2022']
+
+# Renamed column names
+renamed_column_names = column_names[:-1]  # Exclude the last column
+
+# Rename columns
+for i in range(len(renamed_column_names)-1):
+    df.rename(columns= )
+    column_names[i] = renamed_column_names[i+1]
+
+df.columns=column_names
+print(column_names)
+
+# Print the table
+print(df.columns)

Blogpost_IRIS/Remove_extra_lines.py

@@ -0,0 +1,17 @@
+import csv
+
+# Read the CSV file
+with open('C:/Users/SPECTRE/anaconda3/blog.datathinking.org/Blogpost_IRIS/SUIC.csv', 'r') as file:
+    reader = csv.reader(file)
+    lines = list(reader)
+
+# Remove extra values from each line
+for i in range(len(lines)):
+    if len(lines[i]) > 67:
+        lines[i] = lines[i][:67]
+
+# Write the modified lines back to a new CSV file
+with open('modified_file_SUIC.csv', 'w', newline='') as file:
+    writer = csv.writer(file)
+    writer.writerows(lines)
+

Blogpost_IRIS/Remove_quotation.py

@@ -0,0 +1,33 @@
+# Read the modified CSV file
+with open('modified_file_PAT_Res.csv', 'r') as file:
+    lines = file.readlines()
+
+# Process the data and write to a new file
+output_file = 'final_file_PAT_Res.csv'
+
+with open(output_file, 'w') as file:
+    for line in lines:
+        # Remove quotation marks
+        cleaned_line = line.replace('"', '')
+
+        # Replace commas after "Patent application" with "-"
+        cleaned_line = cleaned_line.replace('Patent applications,', 'Patent applications -')
+
+        # Split the line on commas
+        columns = cleaned_line.split(',')
+
+        # Replace empty values with zeros
+        for i in range(len(columns)):
+            if columns[i] == '':
+                columns[i] = '0'
+
+        # Write the modified line to the file
+        file.write(','.join(columns) + '\n')
+
+print(f"Modified data has been written to '{output_file}'.")
+
+
+
+
+
+

Blogpost_IRIS/first_trialFile.py

@@ -0,0 +1,18 @@
+import pandas as pd
+
+# Read the CSV file
+df = pd.read_csv('C:/Users/SPECTRE/anaconda3/blog.datathinking.org/Blogpost_IRIS/modified_file_PAT_Res.csv', delimiter=',', quotechar='"', quoting=3, skipinitialspace=True)
+
+# Remove leading/trailing spaces from column names
+df.columns = df.columns.str.strip()
+
+# Remove quotation marks from values
+df = df.apply(lambda x: x.str.strip('"'))
+
+# Fill empty values with 0
+df = df.fillna(0)
+
+# Display a sample of the data
+print(df.head())
+
+

Blogpost_IRIS/proov4.py

@@ -0,0 +1,11 @@
+import pandas as pd
+with open(r'PAT_Nres.csv', 'r') as infile, \
+     open(r'PAT_Nres.csv', 'w') as outfile:
+    data = infile.read()
+    data = data.replace("\"", "")
+    outfile.write(data)
+# Read the modified file
+df = pd.read_csv('PAT_Nres.csv')
+# Print the table
+print(df[43:50])
+

modified_file_SUIC.csv

@@ -0,0 +1 @@
+"""Country Name","Country Code""""","Indicator Name""""","Indicator Code""""","1960""""","1961""""","1962""""","1963""""","1964""""","1965""""","1966""""","1967""""","1968""""","1969""""","1970""""","1971""""","1972""""","1973""""","1974""""","1975""""","1976""""","1977""""","1978""""","1979""""","1980""""","1981""""","1982""""","1983""""","1984""""","1985""""","1986""""","1987""""","1988""""","1989""""","1990""""","1991""""","1992""""","1993""""","1994""""","1995""""","1996""""","1997""""","1998""""","1999""""","2000""""","2001""""","2002""""","2003""""","2004""""","2005""""","2006""""","2007""""","2008""""","2009""""","2010""""","2011""""","2012""""","2013""""","2014""""","2015""""","2016""""","2017""""","2018""""","2019""""","2020""""","2021""""","2022"""""